2026
Alameda, Cristina; Méndez, Gonzalo; Hervás, Raquel
Multi-Agent Architecture for Formative Assessment: An Integrated Approach to Error Diagnosis and Diagnostic Feedback Proceedings Article Forthcoming
In: 18th International Conference on Computer Supported Education, Scitepress, Forthcoming.
@inproceedings{AlamedaCSEDU2026,
title = {Multi-Agent Architecture for Formative Assessment: An Integrated Approach to Error Diagnosis and Diagnostic Feedback},
author = {Cristina Alameda and Gonzalo M\'{e}ndez and Raquel Herv\'{a}s},
url = {https://nil.fdi.ucm.es/alamedacsedu2026/},
year = {2026},
date = {2026-05-18},
booktitle = {18th International Conference on Computer Supported Education},
publisher = {Scitepress},
abstract = {Intelligent Tutoring Systems demonstrate significant learning gains in mathematics education, yet widespread adoption remains constrained by prohibitive costs and infrastructure requirements that favor well-resourced institutions. Existing LLM-based approaches, while pedagogically promising, depend on high API expenses and cloud connectivity, limiting deployment in under-resourced contexts. We present a multi-agent cognitive architecture for automated formative assessment that operates using sub-2B parameter language models, requiring low resources and local execution. The system coordinates three specialized reasoning agents (abductive, deductive, and inductive) through majority voting, followed by expert student solution analysis and adaptive feedback generation incorporating student modeling and learning history. Evaluation on 1,024 grade-school mathematics problems demonstrates substantial improvements over single-agent baselines: F1-score of 0.907 vs. 0.738 (+22.9), with precision rising from 60.8% to 89.0% (+28.2), and critically reducing false positives from 31.2% to 5.9%, a pedagogically essential improvement for maintaining learners trust. Expert validation by 13 computer scientist and educators confirms superior feedback quality (mean rating 5.2 vs. 3.6, p \< 0.001) across dimensions including diagnostic accuracy, clarity, and pedagogical value, with 63% expert preference for multi-agent feedback. These results challenge the prevailing assumption that effective educational AI requires massive frontier models, demonstrating that thoughtfully orchestrated small language models can deliver pedagogically reliable formative assessment while operating on commodity hardware. By addressing cost and infrastructure barriers, this work aims to democratize adaptive tutoring technologies for global educational equity.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Intelligent Tutoring Systems demonstrate significant learning gains in mathematics education, yet widespread adoption remains constrained by prohibitive costs and infrastructure requirements that favor well-resourced institutions. Existing LLM-based approaches, while pedagogically promising, depend on high API expenses and cloud connectivity, limiting deployment in under-resourced contexts. We present a multi-agent cognitive architecture for automated formative assessment that operates using sub-2B parameter language models, requiring low resources and local execution. The system coordinates three specialized reasoning agents (abductive, deductive, and inductive) through majority voting, followed by expert student solution analysis and adaptive feedback generation incorporating student modeling and learning history. Evaluation on 1,024 grade-school mathematics problems demonstrates substantial improvements over single-agent baselines: F1-score of 0.907 vs. 0.738 (+22.9), with precision rising from 60.8% to 89.0% (+28.2), and critically reducing false positives from 31.2% to 5.9%, a pedagogically essential improvement for maintaining learners trust. Expert validation by 13 computer scientist and educators confirms superior feedback quality (mean rating 5.2 vs. 3.6, p < 0.001) across dimensions including diagnostic accuracy, clarity, and pedagogical value, with 63% expert preference for multi-agent feedback. These results challenge the prevailing assumption that effective educational AI requires massive frontier models, demonstrating that thoughtfully orchestrated small language models can deliver pedagogically reliable formative assessment while operating on commodity hardware. By addressing cost and infrastructure barriers, this work aims to democratize adaptive tutoring technologies for global educational equity.
Alameda, Cristina; Méndez, Gonzalo; Hervás, Raquel
Towards Reliable Reasoning with Multi-Agent Cognitive Collaboration in Small Language Models Proceedings Article
In: Rocha, Ana Paula; Wahde, Mattias; van den Herik, H. Jaap (Ed.): 18th International Conference on Agents and Artificial Intelligence (ICAART2026), pp. 80-91, Scitepress, 2026, ISBN: 978-989-758-796-2.
@inproceedings{AlamedaICAART2026,
title = {Towards Reliable Reasoning with Multi-Agent Cognitive Collaboration in Small Language Models},
author = {Cristina Alameda and Gonzalo M\'{e}ndez and Raquel Herv\'{a}s},
editor = {Ana Paula Rocha and Mattias Wahde and H. Jaap van den Herik},
url = {https://nil.fdi.ucm.es/wp-content/uploads/2026/01/AlamedaICAART2026.pdf},
doi = {10.5220/0014338400004052},
isbn = {978-989-758-796-2},
year = {2026},
date = {2026-03-05},
urldate = {2026-03-05},
booktitle = {18th International Conference on Agents and Artificial Intelligence (ICAART2026)},
volume = {1},
pages = {80-91},
publisher = {Scitepress},
abstract = {Small Language Models offer practical advantages but face critical limitations, including poor self-calibration and inconsistent reasoning. We present MACoMoE (Multi-Agent Cognitive Mixture-of-Experts), a modular framework that addresses these challenges via structured cognitive specialization and collective validation, without increasing model size. The architecture separates reasoning generation from quality assessment across three layers: specialized cognitive reasoners (deductive, inductive, abductive), multi-perspective evaluators (logical validity, epistemic soundness, empirical groundedness), and a decision aggregation layer comparing four consensus mechanisms. Evaluation on 256 reasoning problems on two mathematical datasets shows that voting-based aggregation substantially outperforms self-assessment: Simple Majority achieves 95.7% alignment with ground truth versus 51.4% for self-confidence scoring (+44.3pp). Chain-of-Thought prompting improves accuracy by 29.3pp on MR-GSM8K and 23.4pp on MR-BEN while reducing reasoning steps by 36%, indicating efficiency gains through structured exploration. These results demonstrate that compact models can effectively serve as peer evaluators, and that simple consensus protocols suffice when reasoning diversity is ensured, offering a computationally efficient alternative to individual SLM deployment and costly frontier model ensembles.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Small Language Models offer practical advantages but face critical limitations, including poor self-calibration and inconsistent reasoning. We present MACoMoE (Multi-Agent Cognitive Mixture-of-Experts), a modular framework that addresses these challenges via structured cognitive specialization and collective validation, without increasing model size. The architecture separates reasoning generation from quality assessment across three layers: specialized cognitive reasoners (deductive, inductive, abductive), multi-perspective evaluators (logical validity, epistemic soundness, empirical groundedness), and a decision aggregation layer comparing four consensus mechanisms. Evaluation on 256 reasoning problems on two mathematical datasets shows that voting-based aggregation substantially outperforms self-assessment: Simple Majority achieves 95.7% alignment with ground truth versus 51.4% for self-confidence scoring (+44.3pp). Chain-of-Thought prompting improves accuracy by 29.3pp on MR-GSM8K and 23.4pp on MR-BEN while reducing reasoning steps by 36%, indicating efficiency gains through structured exploration. These results demonstrate that compact models can effectively serve as peer evaluators, and that simple consensus protocols suffice when reasoning diversity is ensured, offering a computationally efficient alternative to individual SLM deployment and costly frontier model ensembles.
Francisco, Virginia; Rodrigo, Covadonga; Iniesto, Francisco; Hervás, Raquel
Cognitive Accessibility in Generative AI Interfaces: A Systematic Review Journal Article
In: International Journal of Human–Computer Interaction, pp. 1-17, 2026.
@article{nokey,
title = {Cognitive Accessibility in Generative AI Interfaces: A Systematic Review},
author = {Virginia Francisco and Covadonga Rodrigo and Francisco Iniesto and Raquel Herv\'{a}s},
editor = {Taylor and Francis},
doi = {10.1080/10447318.2026.2618562},
year = {2026},
date = {2026-01-22},
urldate = {2026-01-22},
journal = {International Journal of Human\textendashComputer Interaction},
pages = {1-17},
abstract = {Generative Artificial Intelligence (GAI) represents a significant shift in the way people interact with technology, with a growing impact in sectors such as education, communication, and content creation. Although its applications promise relevant benefits for people with cognitive disabilities, such as language simplification or support for task organization, there are also significant accessibility challenges that remain unexplored. This paper presents the results of a systematic literature review focused on the cognitive accessibility of textual GAI interfaces. The main objective was to identify the current cognitive accessibility challenges inherent in textual GAI interfaces and to synthesize the solutions proposed to promote a more inclusive interaction. To this end, seven studies selected between 2020 and 2024 from four academic databases (Scopus, Web of Science, IEEE Xplore, and ACM Digital Library) were analyzed. The analysis reveals that current interfaces impose excessive cognitive load and suffer from systemic lack of predictability and user scaffolding due to their reliance on complex prompt engineering and low explainability. Emerging proposals based on inclusive design, personalization, multimodal interfaces, and ethical frameworks are also identified. The paper concludes by highlighting the need for more empirical studies, specific design guidelines, and validated evaluation methods to ensure that generative technologies are truly accessible to all.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Generative Artificial Intelligence (GAI) represents a significant shift in the way people interact with technology, with a growing impact in sectors such as education, communication, and content creation. Although its applications promise relevant benefits for people with cognitive disabilities, such as language simplification or support for task organization, there are also significant accessibility challenges that remain unexplored. This paper presents the results of a systematic literature review focused on the cognitive accessibility of textual GAI interfaces. The main objective was to identify the current cognitive accessibility challenges inherent in textual GAI interfaces and to synthesize the solutions proposed to promote a more inclusive interaction. To this end, seven studies selected between 2020 and 2024 from four academic databases (Scopus, Web of Science, IEEE Xplore, and ACM Digital Library) were analyzed. The analysis reveals that current interfaces impose excessive cognitive load and suffer from systemic lack of predictability and user scaffolding due to their reliance on complex prompt engineering and low explainability. Emerging proposals based on inclusive design, personalization, multimodal interfaces, and ethical frameworks are also identified. The paper concludes by highlighting the need for more empirical studies, specific design guidelines, and validated evaluation methods to ensure that generative technologies are truly accessible to all.
2025
Guasch, Daniel; Rodrigo, Covadonga; Francisco, Virginia; Hervás, Raquel
Roadmap to inclusive Artificial Intelligence for persons with intellectual disability Journal Article
In: Journal of Accessibility and Design for All (JACCES), vol. 15, no. 2, pp. 74-96, 2025, ISBN: 2013-7087.
@article{nokey,
title = {Roadmap to inclusive Artificial Intelligence for persons with intellectual disability},
author = {Daniel Guasch and Covadonga Rodrigo and Virginia Francisco and Raquel Herv\'{a}s},
doi = {https://doi.org/10.17411/jacces.v15i2.625},
isbn = {2013-7087},
year = {2025},
date = {2025-11-11},
urldate = {2025-11-11},
journal = {Journal of Accessibility and Design for All (JACCES)},
volume = {15},
number = {2},
pages = {74-96},
abstract = {The rapid evolution of Artificial Intelligence (AI) poses significant opportunities and challenges for historically discriminated groups, such as persons with intellectual disabilities. This article proposes a conceptual framework that enables an inclusive and accessible approach to designing generative AI systems. Based on an exhaustive review of legislative, socio-health, and technological sources, key concepts such as disability, accessibility, and usability are defined and related, with intellectual disability serving as the central objective of this work. The need to apply principles of Universal Design (UD) and User-Centred Design (UCD) is highlighted to ensure products, environments, and services that are understandable, usable, and customisable. Finally, specific challenges are identified in the development of generative AI tools in Spain for persons with intellectual disabilities, and specific recommendations are proposed to promote inclusive AI for all.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The rapid evolution of Artificial Intelligence (AI) poses significant opportunities and challenges for historically discriminated groups, such as persons with intellectual disabilities. This article proposes a conceptual framework that enables an inclusive and accessible approach to designing generative AI systems. Based on an exhaustive review of legislative, socio-health, and technological sources, key concepts such as disability, accessibility, and usability are defined and related, with intellectual disability serving as the central objective of this work. The need to apply principles of Universal Design (UD) and User-Centred Design (UCD) is highlighted to ensure products, environments, and services that are understandable, usable, and customisable. Finally, specific challenges are identified in the development of generative AI tools in Spain for persons with intellectual disabilities, and specific recommendations are proposed to promote inclusive AI for all.
Corsetti, Barbara; Moreno, Lourdes; Hervás, Raquel
Evaluating Eleuteria App: the deliver stage of an inclusive double diamond design process Proceedings Article
In: 25th International Conference on Human-Computer Interaction (INTERACCIÓN 2025), Asociación Interacción Persona-Ordenador (AIPO), 2025.
@inproceedings{nokey,
title = {Evaluating Eleuteria App: the deliver stage of an inclusive double diamond design process},
author = {Barbara Corsetti and Lourdes Moreno and Raquel Herv\'{a}s},
url = {https://ceur-ws.org/Vol-4000/paper11.pdf},
year = {2025},
date = {2025-09-05},
urldate = {2025-09-05},
booktitle = {25th International Conference on Human-Computer Interaction (INTERACCI\'{O}N 2025)},
publisher = {Asociaci\'{o}n Interacci\'{o}n Persona-Ordenador (AIPO)},
abstract = {Interactive systems are firmly becoming fundamental in daily life, providing users with tools to enhance their autonomy, communication, self-organization, and overall well-being. Due to their helpful impact on users’ lives, interactive systems are increasingly being applied as supportive products for individuals with mild intellectual impairments. Thus, delivering accessible and intuitive interactive solutions tailored to the needs of these individuals is a way to support their autonomy.
This paper presents the findings from the Deliver stage of a design project based on the Double Diamond Model. The focus was to evaluate the prototype of Eleuteria App\textendashan interactive system specifically designed to support individuals with mild intellectual impairments and their caregivers\textendashbefore its implementation and first release. The system enables individuals to manage their income, apply for jobs within or outside their foundation, communicate with family and caregivers, and locate loved ones, while also equipping caregivers with tools to monitor and track those in their care. The evaluation process involved iterative user testing with five individuals with mild intellectual impairments and six caregivers. In addition, three product designers performed a heuristic evaluation (using a checklist aligned with Nielsen’s ten usability principles) to identify design issues and opportunities for improvement. The evaluation revealed strong user engagement and high interest from caregivers, highlighting the need to tailor interaction design for users with intellectual disabilities. These findings
contribute to inclusive design practices by emphasising iterative user testing, adapted evaluation protocols, and the value of early-stage expert input to ensure accessible and engaging digital experiences.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Interactive systems are firmly becoming fundamental in daily life, providing users with tools to enhance their autonomy, communication, self-organization, and overall well-being. Due to their helpful impact on users’ lives, interactive systems are increasingly being applied as supportive products for individuals with mild intellectual impairments. Thus, delivering accessible and intuitive interactive solutions tailored to the needs of these individuals is a way to support their autonomy.
This paper presents the findings from the Deliver stage of a design project based on the Double Diamond Model. The focus was to evaluate the prototype of Eleuteria App–an interactive system specifically designed to support individuals with mild intellectual impairments and their caregivers–before its implementation and first release. The system enables individuals to manage their income, apply for jobs within or outside their foundation, communicate with family and caregivers, and locate loved ones, while also equipping caregivers with tools to monitor and track those in their care. The evaluation process involved iterative user testing with five individuals with mild intellectual impairments and six caregivers. In addition, three product designers performed a heuristic evaluation (using a checklist aligned with Nielsen’s ten usability principles) to identify design issues and opportunities for improvement. The evaluation revealed strong user engagement and high interest from caregivers, highlighting the need to tailor interaction design for users with intellectual disabilities. These findings
contribute to inclusive design practices by emphasising iterative user testing, adapted evaluation protocols, and the value of early-stage expert input to ensure accessible and engaging digital experiences.
This paper presents the findings from the Deliver stage of a design project based on the Double Diamond Model. The focus was to evaluate the prototype of Eleuteria App–an interactive system specifically designed to support individuals with mild intellectual impairments and their caregivers–before its implementation and first release. The system enables individuals to manage their income, apply for jobs within or outside their foundation, communicate with family and caregivers, and locate loved ones, while also equipping caregivers with tools to monitor and track those in their care. The evaluation process involved iterative user testing with five individuals with mild intellectual impairments and six caregivers. In addition, three product designers performed a heuristic evaluation (using a checklist aligned with Nielsen’s ten usability principles) to identify design issues and opportunities for improvement. The evaluation revealed strong user engagement and high interest from caregivers, highlighting the need to tailor interaction design for users with intellectual disabilities. These findings
contribute to inclusive design practices by emphasising iterative user testing, adapted evaluation protocols, and the value of early-stage expert input to ensure accessible and engaging digital experiences.
Francisco, Virginia; Hervás, Raquel; García-Mata, Ricardo
Challenges in Accessing Generative AI for Users with Cognitive Disabilities: An Exploratory Case Study Proceedings Article
In: 25th International Conference on Human-Computer Interaction (INTERACCIÓN 2025), Asociación Interacción Persona-Ordenador (AIPO), 2025.
@inproceedings{nokey,
title = {Challenges in Accessing Generative AI for Users with Cognitive Disabilities: An Exploratory Case Study},
author = {Virginia Francisco and Raquel Herv\'{a}s and Ricardo Garc\'{i}a-Mata},
url = {https://ceur-ws.org/Vol-4000/paper09.pdf},
year = {2025},
date = {2025-09-05},
urldate = {2025-09-05},
booktitle = {25th International Conference on Human-Computer Interaction (INTERACCI\'{O}N 2025)},
publisher = {Asociaci\'{o}n Interacci\'{o}n Persona-Ordenador (AIPO)},
abstract = {Generative Artificial Intelligences (GAIs) have great potential for people with cognitive disabilities, since they can increase their autonomy, offer them personalized learning and break down the barriers that this group raditionally has to access information. To address this gap, this paper investigates the specific difficulties experienced by users with cognitive disabilities when interacting with GAIs.
We present an exploratory case study involving 16 students with cognitive disabilities enrolled in a universitybased educational program. ChatGPT was selected as the representative GAI tool due to its popularity and the similarity of its interface and interaction paradigms to those of other widely used Generative AI systems. The intervention was integrated into the students’ academic curriculum and involved completing practical academic tasks using ChatGPT. A mixed methodological approach was employed, combining pre- and post-intervention questionnaires completed by students and tutors/experts, along with on-site observations during the sessions.
Results of this exploratory study corroborate the existence of remarkable barriers in basic interaction areas: question formulation (69% of students required support), response comprehension (56% reported understanding
answers only occasionally), and information verification (only 19% were able to verify the system responses independently). Suggestions for improvement, from the perspective of the users and their tutor, include more guided interfaces with predefined question templates and contextual suggestions, customizable output formats with language simplification, enhanced spelling correction tools, interactive explanations of complex terms and built-in verification aids.
This study highlights the need to design GAI interfaces with a strong focus on cognitive accessibility. Future development should prioritize multimodal and adaptive interaction models, support tools for comprehension and verification, and interaction designs that promote greater autonomy for users with cognitive disabilities.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Generative Artificial Intelligences (GAIs) have great potential for people with cognitive disabilities, since they can increase their autonomy, offer them personalized learning and break down the barriers that this group raditionally has to access information. To address this gap, this paper investigates the specific difficulties experienced by users with cognitive disabilities when interacting with GAIs.
We present an exploratory case study involving 16 students with cognitive disabilities enrolled in a universitybased educational program. ChatGPT was selected as the representative GAI tool due to its popularity and the similarity of its interface and interaction paradigms to those of other widely used Generative AI systems. The intervention was integrated into the students’ academic curriculum and involved completing practical academic tasks using ChatGPT. A mixed methodological approach was employed, combining pre- and post-intervention questionnaires completed by students and tutors/experts, along with on-site observations during the sessions.
Results of this exploratory study corroborate the existence of remarkable barriers in basic interaction areas: question formulation (69% of students required support), response comprehension (56% reported understanding
answers only occasionally), and information verification (only 19% were able to verify the system responses independently). Suggestions for improvement, from the perspective of the users and their tutor, include more guided interfaces with predefined question templates and contextual suggestions, customizable output formats with language simplification, enhanced spelling correction tools, interactive explanations of complex terms and built-in verification aids.
This study highlights the need to design GAI interfaces with a strong focus on cognitive accessibility. Future development should prioritize multimodal and adaptive interaction models, support tools for comprehension and verification, and interaction designs that promote greater autonomy for users with cognitive disabilities.
We present an exploratory case study involving 16 students with cognitive disabilities enrolled in a universitybased educational program. ChatGPT was selected as the representative GAI tool due to its popularity and the similarity of its interface and interaction paradigms to those of other widely used Generative AI systems. The intervention was integrated into the students’ academic curriculum and involved completing practical academic tasks using ChatGPT. A mixed methodological approach was employed, combining pre- and post-intervention questionnaires completed by students and tutors/experts, along with on-site observations during the sessions.
Results of this exploratory study corroborate the existence of remarkable barriers in basic interaction areas: question formulation (69% of students required support), response comprehension (56% reported understanding
answers only occasionally), and information verification (only 19% were able to verify the system responses independently). Suggestions for improvement, from the perspective of the users and their tutor, include more guided interfaces with predefined question templates and contextual suggestions, customizable output formats with language simplification, enhanced spelling correction tools, interactive explanations of complex terms and built-in verification aids.
This study highlights the need to design GAI interfaces with a strong focus on cognitive accessibility. Future development should prioritize multimodal and adaptive interaction models, support tools for comprehension and verification, and interaction designs that promote greater autonomy for users with cognitive disabilities.
Bousnitra, Walid; Hervás, Raquel; Díaz, Alberto; Leo, Daniel; Martín, Carlos; Sosa, Sirma
Self-guided interpretation of images for blind users based on multi-layered interaction Journal Article
In: Universal Access in the Information Society, vol. 24, pp. 3165–3183, 2025, ISSN: 1615-5297.
@article{Bousnitra2025,
title = {Self-guided interpretation of images for blind users based on multi-layered interaction},
author = {Walid Bousnitra and Raquel Herv\'{a}s and Alberto D\'{i}az and Daniel Leo and Carlos Mart\'{i}n and Sirma Sosa},
doi = {10.1007/s10209-025-01256-w},
issn = {1615-5297},
year = {2025},
date = {2025-09-02},
urldate = {2025-09-02},
journal = {Universal Access in the Information Society},
volume = {24},
pages = {3165\textendash3183},
publisher = {Springer Science and Business Media LLC},
abstract = {Image spatial composition, information about the number of objects and their characteristics, and additional details such as the colors and attributes of the people in the scene can provide additional information in an image or photograph. However, the usual approaches to make images accessible to blind persons focus mainly on describing the image’s content, without inquiring into other aspects such as spatial composition, colors, background, known faces, etc. In doing so, much information that is present in the image but not included in the description is missing for a blind user. This work explores the combination of image captioning and object detection techniques with the final goal of making images more accessible to blind users. The approach is twofold: (1) state-of-the-art algorithms of image captioning and object detection will be combined so blind users can extract different kinds of information from a given image; and (2) blind users will guide the exploration of the images, so they can gather all the information in a personalized manner and make their own interpretation. This novel interaction is designed as a self-guided multi-layered approach, enabling blind users to personalize their exploration of image content by both guiding the process and accessing the different layers of information as desired. We implemented a mobile application based on requirements obtained from blind users and performed an evaluation that provided promising results. The participants were reasonably satisfied with the usability of the prototype, and in general they were able to gather additional information through their tactile exploration that was not present in the initial image descriptions. However, some issues that were detected in the evaluation, and functionalities that could not be implemented, will be addressed in future work.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Image spatial composition, information about the number of objects and their characteristics, and additional details such as the colors and attributes of the people in the scene can provide additional information in an image or photograph. However, the usual approaches to make images accessible to blind persons focus mainly on describing the image’s content, without inquiring into other aspects such as spatial composition, colors, background, known faces, etc. In doing so, much information that is present in the image but not included in the description is missing for a blind user. This work explores the combination of image captioning and object detection techniques with the final goal of making images more accessible to blind users. The approach is twofold: (1) state-of-the-art algorithms of image captioning and object detection will be combined so blind users can extract different kinds of information from a given image; and (2) blind users will guide the exploration of the images, so they can gather all the information in a personalized manner and make their own interpretation. This novel interaction is designed as a self-guided multi-layered approach, enabling blind users to personalize their exploration of image content by both guiding the process and accessing the different layers of information as desired. We implemented a mobile application based on requirements obtained from blind users and performed an evaluation that provided promising results. The participants were reasonably satisfied with the usability of the prototype, and in general they were able to gather additional information through their tactile exploration that was not present in the initial image descriptions. However, some issues that were detected in the evaluation, and functionalities that could not be implemented, will be addressed in future work.
Corsetti, Barbara; Hervás, Raquel; Moreno, Lourdes
Eleuteria App: Designing an Interactive System to Support Individuals with Mild Intellectual Disabilities Journal Article
In: Universal Access in the Information Society, vol. 24, pp. 3271–3288, 2025, ISSN: 1615-5297.
@article{nokey,
title = {Eleuteria App: Designing an Interactive System to Support Individuals with Mild Intellectual Disabilities},
author = {Barbara Corsetti and Raquel Herv\'{a}s and Lourdes Moreno},
doi = { https://doi.org/10.1007/s10209-025-01247-x},
issn = {1615-5297},
year = {2025},
date = {2025-08-08},
urldate = {2025-08-08},
journal = {Universal Access in the Information Society},
volume = {24},
pages = {3271\textendash3288},
abstract = {Interactive systems improve accessibility in various daily scenarios. This has led to an increasing emphasis on designing and prototyping technologies tailored for individuals with intellectual disabilities. In this context, incorporating diverse perspectives during the design process ensures the systems address needs effectively and inclusively. This paper focuses on creating a supportive system, called Eleuteria App, to allow individuals with mild intellectual disabilities to be more autonomous and independent. The work follows the Double Diamond model requirements presenting an iterative and multi-step methodology for the Develop stage, highlighting the collaborative integration of observations from various stakeholders - including individuals with mild intellectual disabilities, caregivers, developers, accessibility experts, and researchers - to deliver an impactful supportive system. Building on the Define stage explored in previous research, this study proposes a structured methodology for the Develop stage involving four critical steps: (1) the development of a high-fidelity prototype; (2) a comprehensive validation by accessibility experts; (3) user testing involving both designers and developers; and (4) the update of the prototype according to the received feedback. The sessions with accessibility experts focused on ensuring the prototype met accessibility standards, such as WCAG compliance and plain language principles. At the same time, the involvement of designers and developers provided insights into practical usability and technical viability. The findings demonstrate that integrating diverse perspectives\textendashparticularly those of designers, accessibility experts, and developers\textendashis crucial in crafting an accessible, user-friendly interactive system for individuals with mild intellectual impairments. Based on feedback from all evaluators, significant enhancements were made in the app to better align with their recommendations.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Interactive systems improve accessibility in various daily scenarios. This has led to an increasing emphasis on designing and prototyping technologies tailored for individuals with intellectual disabilities. In this context, incorporating diverse perspectives during the design process ensures the systems address needs effectively and inclusively. This paper focuses on creating a supportive system, called Eleuteria App, to allow individuals with mild intellectual disabilities to be more autonomous and independent. The work follows the Double Diamond model requirements presenting an iterative and multi-step methodology for the Develop stage, highlighting the collaborative integration of observations from various stakeholders - including individuals with mild intellectual disabilities, caregivers, developers, accessibility experts, and researchers - to deliver an impactful supportive system. Building on the Define stage explored in previous research, this study proposes a structured methodology for the Develop stage involving four critical steps: (1) the development of a high-fidelity prototype; (2) a comprehensive validation by accessibility experts; (3) user testing involving both designers and developers; and (4) the update of the prototype according to the received feedback. The sessions with accessibility experts focused on ensuring the prototype met accessibility standards, such as WCAG compliance and plain language principles. At the same time, the involvement of designers and developers provided insights into practical usability and technical viability. The findings demonstrate that integrating diverse perspectives–particularly those of designers, accessibility experts, and developers–is crucial in crafting an accessible, user-friendly interactive system for individuals with mild intellectual impairments. Based on feedback from all evaluators, significant enhancements were made in the app to better align with their recommendations.
Jerry, Blessing; Moreno, Lourdes; Francisco, Virginia; Hervás, Raquel
LLM-Driven Accessible Interfaces: A Model-Based Approach Proceedings Article
In: EMUXAI Workshop: Engineering Methods for HCI and UX in AI-Driven Systems (Interact 2025), IFIP-TC13, Belo Horizonte, Minas Gerais, Brazil, 2025.
@inproceedings{nokey,
title = {LLM-Driven Accessible Interfaces: A Model-Based Approach},
author = {Blessing Jerry and Lourdes Moreno and Virginia Francisco and Raquel Herv\'{a}s},
url = {https://arxiv.org/abs/2601.06616
https://doi.org/10.48550/arXiv.2601.06616},
doi = {10.48550/arXiv.2601.06616},
year = {2025},
date = {2025-07-18},
urldate = {2025-07-18},
booktitle = {EMUXAI Workshop: Engineering Methods for HCI and UX in AI-Driven Systems (Interact 2025)},
publisher = {IFIP-TC13},
address = {Belo Horizonte, Minas Gerais, Brazil},
abstract = {The integration of Large Language Models (LLMs) into interactive systems opens new opportunities for adaptive user experiences, yet it also raises challenges regarding accessibility, explainability, and normative compliance. This paper presents an implemented model-driven architecture for generating personalised, multimodal, and accessibility-aligned user interfaces. The approach combines structured user profiles, declarative adaptation rules, and validated prompt templates to refine baseline accessible UI templates that conform to WCAG 2.2 and EN 301 549, tailored to cognitive and sensory support needs. LLMs dynamically transform language complexity, modality, and visual structure, producing outputs such as Plain-Language text, pictograms, and high-contrast layouts aligned with ISO 24495-1 and W3C COGA guidance. A healthcare use case demonstrates how the system generates accessible post-consultation medication instructions tailored to a user profile comprising cognitive disability and hearing impairment. SysML v2 models provide explicit traceability between user needs, adaptation rules, and normative requirements, ensuring explainable and auditable transformations. Grounded in Human-Centered AI (HCAI), the framework incorporates co-design processes and structured feedback mechanisms to guide iterative refinement and support trustworthy generative behaviour.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The integration of Large Language Models (LLMs) into interactive systems opens new opportunities for adaptive user experiences, yet it also raises challenges regarding accessibility, explainability, and normative compliance. This paper presents an implemented model-driven architecture for generating personalised, multimodal, and accessibility-aligned user interfaces. The approach combines structured user profiles, declarative adaptation rules, and validated prompt templates to refine baseline accessible UI templates that conform to WCAG 2.2 and EN 301 549, tailored to cognitive and sensory support needs. LLMs dynamically transform language complexity, modality, and visual structure, producing outputs such as Plain-Language text, pictograms, and high-contrast layouts aligned with ISO 24495-1 and W3C COGA guidance. A healthcare use case demonstrates how the system generates accessible post-consultation medication instructions tailored to a user profile comprising cognitive disability and hearing impairment. SysML v2 models provide explicit traceability between user needs, adaptation rules, and normative requirements, ensuring explainable and auditable transformations. Grounded in Human-Centered AI (HCAI), the framework incorporates co-design processes and structured feedback mechanisms to guide iterative refinement and support trustworthy generative behaviour.
Corsetti, Barbara; Moreno, Lourdes; Hervás, Raquel
Bridging Gaps in Design Thinking: Inclusive Guidelines for Intellectual Disabilities Journal Article
In: International Journal of Human–Computer Interaction, pp. 1–20, 2025.
@article{Corsetti17072025,
title = {Bridging Gaps in Design Thinking: Inclusive Guidelines for Intellectual Disabilities},
author = {Barbara Corsetti and Lourdes Moreno and Raquel Herv\'{a}s},
url = {https://www.tandfonline.com/doi/abs/10.1080/10447318.2025.2527848
https://doi.org/10.1080/10447318.2025.2527848},
doi = {10.1080/10447318.2025.2527848},
year = {2025},
date = {2025-07-17},
urldate = {2025-07-17},
journal = {International Journal of Human\textendashComputer Interaction},
pages = {1\textendash20},
publisher = {Taylor \& Francis},
abstract = {The Design Thinking framework has often been underexplored in its application to individuals with intellectual disabilities, requiring specific adaptations to enhance inclusivity and accessibility. This article explores the adaptation of the Design Thinking framework to better meet the needs of individuals with intellectual disabilities. Recognising that the framework is often underexplored for this group, the study proposes inclusive guidelines developed through a literature review and an explorative study involving 15 participants. Key focus areas include tailored communication, accessible supports, interdisciplinary collaboration, and ethical considerations. These guidelines were validated through a case study on modifying the Empathy Map tool, which showed improved empathy, engagement, and data accuracy. The findings highlight the framework’s potential for more inclusive design practices and offer practical insights to enhance accessibility in the design process for individuals with intellectual disabilities.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The Design Thinking framework has often been underexplored in its application to individuals with intellectual disabilities, requiring specific adaptations to enhance inclusivity and accessibility. This article explores the adaptation of the Design Thinking framework to better meet the needs of individuals with intellectual disabilities. Recognising that the framework is often underexplored for this group, the study proposes inclusive guidelines developed through a literature review and an explorative study involving 15 participants. Key focus areas include tailored communication, accessible supports, interdisciplinary collaboration, and ethical considerations. These guidelines were validated through a case study on modifying the Empathy Map tool, which showed improved empathy, engagement, and data accuracy. The findings highlight the framework’s potential for more inclusive design practices and offer practical insights to enhance accessibility in the design process for individuals with intellectual disabilities.
2024
Hervás, Raquel; Francisco, Virginia
Proyecto IDiLyCo. Tecnologías Lingüísticas para la Inclusión Digital con un Enfoque Centrado en el Usuario Journal Article
In: Revista de la Asociación Interacción Persona Ordenador (AIPO), vol. 5, no. 1, pp. 31–43, 2024, ISSN: 2695-6578.
@article{hervas2024proyecto,
title = {Proyecto IDiLyCo. Tecnolog\'{i}as Ling\"{u}\'{i}sticas para la Inclusi\'{o}n Digital con un Enfoque Centrado en el Usuario},
author = {Raquel Herv\'{a}s and Virginia Francisco},
url = {https://revista.aipo.es/index.php/INTERACCION/article/view/112},
issn = {2695-6578},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {Revista de la Asociaci\'{o}n Interacci\'{o}n Persona Ordenador (AIPO)},
volume = {5},
number = {1},
pages = {31\textendash43},
abstract = {The IDiLyCo project aims to facilitate communication and access to digital information for people with disabilities who face language difficulties. Based on previous experiences in natural language generation and processing, the project develops technological solutions to promote digital inclusion in a simple and configurable way following a user-centered design methodology. Areas explored include text simplification, which allows complex texts to be rewritten in simpler ways; summary generation, which condenses the essential components of a text; augmentative and alternative communication, which facilitates communication for users who cannot use natural language; and emotion analysis, which identifies and clarifies emotions in a text. IDiLyCo focuses on bringing these innovations closer to final users through an ecosystem of services that facilitate digital inclusion and configurable applications according to the needs of each user. This allows people with disabilities to access tools adapted to their needs and developers to integrate these services into their implementations. All applications and services of the project are free and open to use.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The IDiLyCo project aims to facilitate communication and access to digital information for people with disabilities who face language difficulties. Based on previous experiences in natural language generation and processing, the project develops technological solutions to promote digital inclusion in a simple and configurable way following a user-centered design methodology. Areas explored include text simplification, which allows complex texts to be rewritten in simpler ways; summary generation, which condenses the essential components of a text; augmentative and alternative communication, which facilitates communication for users who cannot use natural language; and emotion analysis, which identifies and clarifies emotions in a text. IDiLyCo focuses on bringing these innovations closer to final users through an ecosystem of services that facilitate digital inclusion and configurable applications according to the needs of each user. This allows people with disabilities to access tools adapted to their needs and developers to integrate these services into their implementations. All applications and services of the project are free and open to use.
Hervás, Raquel; Francisco, Virginia; Concepción, Eugenio; Sevilla, Antonio F. G.; Méndez, Gonzalo
Creating an API Ecosystem for Assistive Technologies Oriented to Cognitive Disabilities Journal Article
In: IEEE Access, vol. 12, pp. 163224-163240, 2024, ISSN: 2169-3536.
@article{hervas2024creating,
title = {Creating an API Ecosystem for Assistive Technologies Oriented to Cognitive Disabilities},
author = {Raquel Herv\'{a}s and Virginia Francisco and Eugenio Concepci\'{o}n and Antonio F. G. Sevilla and Gonzalo M\'{e}ndez},
url = {https://ieeexplore.ieee.org/document/10737890},
doi = {10.1109/ACCESS.2024.3487308},
issn = {2169-3536},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {IEEE Access},
volume = {12},
pages = {163224-163240},
publisher = {IEEE},
abstract = {This paper presents the development and implementation of an API (Application Programming Interface) ecosystem designed to support the creation of assistive technologies for individuals with cognitive disabilities. Leveraging the principles of microservices and an API-centered approach, this ecosystem enhances collaboration among developers, reduces the cost of creating accessible tools, and provides highly adaptable and customizable applications. The study details architectural decisions, including the use of GraphQL for flexibility, and demonstrates the benefits of a service-based architecture for digital inclusion. Case studies illustrate the practical applications, showing how this approach facilitates the development and promotes more accessible digital solutions. The findings suggest that this ecosystem can significantly reduce the time and resources needed to develop assistive technologies, potentially accelerating their adoption in domains such as education, healthcare, and daily living aids. The modular and flexible nature of the API ecosystem supports the rapid development of personalized assistive tools, fosters collaborative development, and ensures cross-platform compatibility. These features contribute to creating robust solutions that address diverse user needs across various devices. The ongoing evolution of the API ecosystem, including the integration of advanced management frameworks, promises further innovation and collaboration in assistive technologies. Future work will focus on implementing a comprehensive API management infrastructure to enhance scalability, security, and monitoring capabilities, including the integration and validation of the ecosystem with third-party applications, and so demonstrating its versatility and scalability in real-world scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents the development and implementation of an API (Application Programming Interface) ecosystem designed to support the creation of assistive technologies for individuals with cognitive disabilities. Leveraging the principles of microservices and an API-centered approach, this ecosystem enhances collaboration among developers, reduces the cost of creating accessible tools, and provides highly adaptable and customizable applications. The study details architectural decisions, including the use of GraphQL for flexibility, and demonstrates the benefits of a service-based architecture for digital inclusion. Case studies illustrate the practical applications, showing how this approach facilitates the development and promotes more accessible digital solutions. The findings suggest that this ecosystem can significantly reduce the time and resources needed to develop assistive technologies, potentially accelerating their adoption in domains such as education, healthcare, and daily living aids. The modular and flexible nature of the API ecosystem supports the rapid development of personalized assistive tools, fosters collaborative development, and ensures cross-platform compatibility. These features contribute to creating robust solutions that address diverse user needs across various devices. The ongoing evolution of the API ecosystem, including the integration of advanced management frameworks, promises further innovation and collaboration in assistive technologies. Future work will focus on implementing a comprehensive API management infrastructure to enhance scalability, security, and monitoring capabilities, including the integration and validation of the ecosystem with third-party applications, and so demonstrating its versatility and scalability in real-world scenarios.
Hervás, Raquel; Díaz, Alberto; Amor, Matías; Chaves, Alberto; Ruiz, Víctor
Self-guided Spatial Composition as an Additional Layer of Information to Enhance Accessibility of Images for Blind Users Proceedings Article
In: Proceedings of the XXIV International Conference on Human Computer Interaction, pp. 1–8, 2024.
@inproceedings{hervas2024self,
title = {Self-guided Spatial Composition as an Additional Layer of Information to Enhance Accessibility of Images for Blind Users},
author = {Raquel Herv\'{a}s and Alberto D\'{i}az and Mat\'{i}as Amor and Alberto Chaves and V\'{i}ctor Ruiz},
url = {https://dl.acm.org/doi/pdf/10.1145/3657242.3658590},
doi = {10.1145/3657242.3658590},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Proceedings of the XXIV International Conference on Human Computer Interaction},
pages = {1\textendash8},
abstract = {Image spatial composition can provide additional information in an image or photograph. However, the usual approaches to make images accessible to blind people focus mainly on describing the image’s content, without delving into other aspects such as spatial composition, colors, background, known faces, etc. In doing so, much information that is present in the image but not included in the description is missing for a blind user. This work explores the combination of image captioning and object detection techniques with the final goal of making images more accessible to blind users. The approach is twofold: (1) state-of-the-art algorithms of image captioning and object detection will be combined so blind users can visualize the spatial composition of a given image; and (2) blind users will guide the exploration of the images, so they can gather all the information in a personalized manner and make their own interpretation. We implemented a preliminary prototype based on requirements obtained from blind users and performed an evaluation that provided promising results. The participants were reasonably satisfied with the usability of the prototype, and in several cases, they were able to obtain more information during their self-guided exploration of the images than with the general original description. However, some issues that were detected in the evaluation, and functionalities that could not be implemented, will be addressed in future work.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Image spatial composition can provide additional information in an image or photograph. However, the usual approaches to make images accessible to blind people focus mainly on describing the image’s content, without delving into other aspects such as spatial composition, colors, background, known faces, etc. In doing so, much information that is present in the image but not included in the description is missing for a blind user. This work explores the combination of image captioning and object detection techniques with the final goal of making images more accessible to blind users. The approach is twofold: (1) state-of-the-art algorithms of image captioning and object detection will be combined so blind users can visualize the spatial composition of a given image; and (2) blind users will guide the exploration of the images, so they can gather all the information in a personalized manner and make their own interpretation. We implemented a preliminary prototype based on requirements obtained from blind users and performed an evaluation that provided promising results. The participants were reasonably satisfied with the usability of the prototype, and in several cases, they were able to obtain more information during their self-guided exploration of the images than with the general original description. However, some issues that were detected in the evaluation, and functionalities that could not be implemented, will be addressed in future work.
Corsetti, Barbara; Moreno, Lourdes; Hervás, Raquel
Shaping Interactive Systems: Defining Features to Meet the Needs of Individuals with Mild Intellectual Disabilities Proceedings Article
In: Proceedings of the XXIV International Conference on Human Computer Interaction, pp. 1–8, 2024.
@inproceedings{corsetti2024shaping,
title = {Shaping Interactive Systems: Defining Features to Meet the Needs of Individuals with Mild Intellectual Disabilities},
author = {Barbara Corsetti and Lourdes Moreno and Raquel Herv\'{a}s},
url = {https://dl.acm.org/doi/10.1145/3657242.3658593},
doi = {10.1145/3657242.3658593},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Proceedings of the XXIV International Conference on Human Computer Interaction},
pages = {1\textendash8},
abstract = {Given the significant potential of interactive systems to enhance daily accessibility through user-friendly interfaces, there is a growing interest in addressing these technologies to individuals with intellectual disabilities. Hence, many researchers and designers are currently focused on carrying out User Experience (UX) design processes to develop supportive interactive systems. This paper explores the development of interactive systems tailored to the unique needs of individuals with mild intellectual disabilities. This paper outlines a case study focused on the early stages of a design project within the Double Diamond design model. Thus, it details a structured methodology for the Define phase, emphasizing the collaborative synthesis of diverse stakeholder perspectives (e.g., individuals with intellectual disabilities, caregivers, developers, and researchers) to identify impactful system features. The emphasis is mainly on the Definition stage of the model, where various tools, techniques, and research activities for interactive design are applied to define the system’s characteristics. Following the Discover stage detailed in previous research, this paper focuses on the subsequent Definition stage, highlighting the importance of incorporating diverse perspectives, including those of caregivers and developers. The findings underline that engaging multiple stakeholders significantly enhances the design process, leading to the selection of impactful and viable features for a supportive system addressed to individuals with mild intellectual impairments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Given the significant potential of interactive systems to enhance daily accessibility through user-friendly interfaces, there is a growing interest in addressing these technologies to individuals with intellectual disabilities. Hence, many researchers and designers are currently focused on carrying out User Experience (UX) design processes to develop supportive interactive systems. This paper explores the development of interactive systems tailored to the unique needs of individuals with mild intellectual disabilities. This paper outlines a case study focused on the early stages of a design project within the Double Diamond design model. Thus, it details a structured methodology for the Define phase, emphasizing the collaborative synthesis of diverse stakeholder perspectives (e.g., individuals with intellectual disabilities, caregivers, developers, and researchers) to identify impactful system features. The emphasis is mainly on the Definition stage of the model, where various tools, techniques, and research activities for interactive design are applied to define the system’s characteristics. Following the Discover stage detailed in previous research, this paper focuses on the subsequent Definition stage, highlighting the importance of incorporating diverse perspectives, including those of caregivers and developers. The findings underline that engaging multiple stakeholders significantly enhances the design process, leading to the selection of impactful and viable features for a supportive system addressed to individuals with mild intellectual impairments.
León, Carlos; Alcaide, Beatriz; Bautista, Susana; Francisco, Virginia; Hervás, Raquel; Méndez, Gonzalo; Sánchez-Horcajuelo, Rocío; Trefftz, Nicolás Emmanuel; Villar, Alejandro
Adaptación de material curricular de herramientas TIC para la diversidad funcional en carreras STEM Journal Article
In: 2024.
@article{leon2024adaptacion,
title = {Adaptaci\'{o}n de material curricular de herramientas TIC para la diversidad funcional en carreras STEM},
author = {Carlos Le\'{o}n and Beatriz Alcaide and Susana Bautista and Virginia Francisco and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez and Roc\'{i}o S\'{a}nchez-Horcajuelo and Nicol\'{a}s Emmanuel Trefftz and Alejandro Villar},
url = {https://hdl.handle.net/20.500.14352/105786
https://docta.ucm.es/bitstreams/165977ed-08d4-4986-a2ac-4eda619d3129/download},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
abstract = {El proyecto propone aportar valor en el proceso de aprendizaje de forma acumulativa (creando una base de datos de informaci\'{o}n que pueda ser reutilizada a\~{n}o tras a\~{n}o), involucrar a los estudiantes en el proceso de generaci\'{o}n y actualizaci\'{o}n de conocimiento, y tener en cuenta, con medidas concretas, la diversidad funcional de los estudiantes. M\'{a}s concretamente, en el proyecto se contempla implementar un prototipo de portal web y probar su resultado de forma experimental en 2 asignaturas en el curso 2023-2024 en la Facultad de Inform\'{a}tica de la Universidad Complutense de Madrid.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
El proyecto propone aportar valor en el proceso de aprendizaje de forma acumulativa (creando una base de datos de información que pueda ser reutilizada año tras año), involucrar a los estudiantes en el proceso de generación y actualización de conocimiento, y tener en cuenta, con medidas concretas, la diversidad funcional de los estudiantes. Más concretamente, en el proyecto se contempla implementar un prototipo de portal web y probar su resultado de forma experimental en 2 asignaturas en el curso 2023-2024 en la Facultad de Informática de la Universidad Complutense de Madrid.
Francisco, Virginia; Hervás, Raquel; Bel, María Cristina; Carpintero, María Elvira; Álvarez, Raul; Corsetti, Barbara; Beunza, Silvia
DAIDI: diseñando aplicaciones informáticas para personas con discapacidad intelectual (ApS 2023-24) Journal Article
In: 2024.
@article{francisco2024daidi,
title = {DAIDI: dise\~{n}ando aplicaciones inform\'{a}ticas para personas con discapacidad intelectual (ApS 2023-24)},
author = {Virginia Francisco and Raquel Herv\'{a}s and Mar\'{i}a Cristina Bel and Mar\'{i}a Elvira Carpintero and Raul \'{A}lvarez and Barbara Corsetti and Silvia Beunza},
url = {https://hdl.handle.net/20.500.14352/108489
https://docta.ucm.es/bitstreams/1f8f49dc-ae5c-4016-ba6f-37035ae9a412/download},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
abstract = {El objetivo del proyecto DAIDI era crear aplicaciones inform\'{a}ticas que cubran necesidades reales de personas con discapacidad intelectual. Para conseguir este objetivo el proyecto constaba de las siguientes fases:
1. Los estudiantes del programa ACCEDE (programa formativo de la Facultad de Educaci\'{o}n de la UCM para j\'{o}venes con discapacidad intelectual) y varias entidades de personas con discapacidad intelectual (Aspace Segovia, Fundaci\'{o}n Esfera y el colegio Estudio3-AFANIAS) propondr\'{a}n aplicaciones que cubran necesidades reales de este colectivo.
2. En una de las primeras clases de la asignatura DSI (Dise\~{n}o de Sistemas Interactivos, Grado en Ingenier\'{i}a Inform\'{a}tica), los estudiantes del programa ACCEDE y las entidades presentar\'{a}n sus propuestas. Una vez presentadas las propuestas, los estudiantes de DSI elegir\'{a}n en cuales de los proyectos propuestos desean trabajar.
3. Los estudiantes de DSI, durante el primer cuatrimestre, realizar\'{a}n el dise\~{n}o de las aplicaciones seleccionadas. Para realizar este dise\~{n}o, los estudiantes mantendr\'{a}n un contacto estrecho con las entidades y los estudiantes de ACCEDE, para obtener los requisitos de la aplicaci\'{o}n y para realizar una evaluaci\'{o}n del prototipo de dise\~{n}o creado al final de la asignatura.
4. En el segundo cuatrimestre, los estudiantes de la asignatura GPS (Gesti\'{o}n de Proyectos Software y metodolog\'{i}as de desarrollo, Grado en Ingenier\'{i}a del Software), dar\'{a}n funcionalidad a los prototipos de dise\~{n}o creados en DSI. Durante el segundo cuatrimestre tambi\'{e}n habr\'{a} contacto con las entidades y los estudiantes del programa ACCEDE que dar\'{a}n feedback sobre las aplicaciones creadas. Los estudiantes del programa ACCEDE y los usuarios finales de las entidades implicadas examinar\'{a}n las aplicaciones con el objetivo de conseguir sistemas que realmente tenga en cuenta las necesidades y limitaciones de los usuarios finales.
5. A final de curso, se convocar\'{a} a las entidades y a los estudiantes del programa ACCEDE y de las asignaturas implicadas (DSI y GPS) para presentar p\'{u}blicamente las aplicaciones creadas. Estas aplicaciones estar\'{a}n disponibles para todo aquel que desee utilizarlas.
},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
El objetivo del proyecto DAIDI era crear aplicaciones informáticas que cubran necesidades reales de personas con discapacidad intelectual. Para conseguir este objetivo el proyecto constaba de las siguientes fases:
1. Los estudiantes del programa ACCEDE (programa formativo de la Facultad de Educación de la UCM para jóvenes con discapacidad intelectual) y varias entidades de personas con discapacidad intelectual (Aspace Segovia, Fundación Esfera y el colegio Estudio3-AFANIAS) propondrán aplicaciones que cubran necesidades reales de este colectivo.
2. En una de las primeras clases de la asignatura DSI (Diseño de Sistemas Interactivos, Grado en Ingeniería Informática), los estudiantes del programa ACCEDE y las entidades presentarán sus propuestas. Una vez presentadas las propuestas, los estudiantes de DSI elegirán en cuales de los proyectos propuestos desean trabajar.
3. Los estudiantes de DSI, durante el primer cuatrimestre, realizarán el diseño de las aplicaciones seleccionadas. Para realizar este diseño, los estudiantes mantendrán un contacto estrecho con las entidades y los estudiantes de ACCEDE, para obtener los requisitos de la aplicación y para realizar una evaluación del prototipo de diseño creado al final de la asignatura.
4. En el segundo cuatrimestre, los estudiantes de la asignatura GPS (Gestión de Proyectos Software y metodologías de desarrollo, Grado en Ingeniería del Software), darán funcionalidad a los prototipos de diseño creados en DSI. Durante el segundo cuatrimestre también habrá contacto con las entidades y los estudiantes del programa ACCEDE que darán feedback sobre las aplicaciones creadas. Los estudiantes del programa ACCEDE y los usuarios finales de las entidades implicadas examinarán las aplicaciones con el objetivo de conseguir sistemas que realmente tenga en cuenta las necesidades y limitaciones de los usuarios finales.
5. A final de curso, se convocará a las entidades y a los estudiantes del programa ACCEDE y de las asignaturas implicadas (DSI y GPS) para presentar públicamente las aplicaciones creadas. Estas aplicaciones estarán disponibles para todo aquel que desee utilizarlas.
1. Los estudiantes del programa ACCEDE (programa formativo de la Facultad de Educación de la UCM para jóvenes con discapacidad intelectual) y varias entidades de personas con discapacidad intelectual (Aspace Segovia, Fundación Esfera y el colegio Estudio3-AFANIAS) propondrán aplicaciones que cubran necesidades reales de este colectivo.
2. En una de las primeras clases de la asignatura DSI (Diseño de Sistemas Interactivos, Grado en Ingeniería Informática), los estudiantes del programa ACCEDE y las entidades presentarán sus propuestas. Una vez presentadas las propuestas, los estudiantes de DSI elegirán en cuales de los proyectos propuestos desean trabajar.
3. Los estudiantes de DSI, durante el primer cuatrimestre, realizarán el diseño de las aplicaciones seleccionadas. Para realizar este diseño, los estudiantes mantendrán un contacto estrecho con las entidades y los estudiantes de ACCEDE, para obtener los requisitos de la aplicación y para realizar una evaluación del prototipo de diseño creado al final de la asignatura.
4. En el segundo cuatrimestre, los estudiantes de la asignatura GPS (Gestión de Proyectos Software y metodologías de desarrollo, Grado en Ingeniería del Software), darán funcionalidad a los prototipos de diseño creados en DSI. Durante el segundo cuatrimestre también habrá contacto con las entidades y los estudiantes del programa ACCEDE que darán feedback sobre las aplicaciones creadas. Los estudiantes del programa ACCEDE y los usuarios finales de las entidades implicadas examinarán las aplicaciones con el objetivo de conseguir sistemas que realmente tenga en cuenta las necesidades y limitaciones de los usuarios finales.
5. A final de curso, se convocará a las entidades y a los estudiantes del programa ACCEDE y de las asignaturas implicadas (DSI y GPS) para presentar públicamente las aplicaciones creadas. Estas aplicaciones estarán disponibles para todo aquel que desee utilizarlas.
2023
Corsetti, Barbara; Hervás, Raquel; Moreno, Lourdes
Knowing Users with Mild Intellectual Impairments in UX Design Processes Proceedings Article
In: XXIII International Conference on Human Computer Interaction, Interaccion 2023, Lleida, Spain, September 4-6, 2023, pp. 8:1–8:8, ACM, 2023.
@inproceedings{DBLP:conf/interaccion/CorsettiB023,
title = {Knowing Users with Mild Intellectual Impairments in UX Design Processes},
author = {Barbara Corsetti and Raquel Herv\'{a}s and Lourdes Moreno},
url = {https://doi.org/10.1145/3612783.3612792},
doi = {10.1145/3612783.3612792},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {XXIII International Conference on Human Computer Interaction, Interaccion
2023, Lleida, Spain, September 4-6, 2023},
pages = {8:1\textendash8:8},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2022
Francisco, Virginia; Moreno-Ger, Pablo; Hervás, Raquel
Application of competitive activities to improve students’ participation Journal Article
In: IEEE Transactions on Learning Technologies, vol. 15, no. 1, pp. 2–14, 2022, ISSN: 1939-1382.
@article{francisco2022application,
title = {Application of competitive activities to improve students’ participation},
author = {Virginia Francisco and Pablo Moreno-Ger and Raquel Herv\'{a}s},
url = {https://ieeexplore.ieee.org/iel7/4620076/4620077/09720233.pdf},
doi = {10.1109/TLT.2022.3153174},
issn = {1939-1382},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Learning Technologies},
volume = {15},
number = {1},
pages = {2\textendash14},
publisher = {IEEE},
abstract = {Making students become intrinsically motivated to participate in daily class activities is an open challenge that has been addressed in different ways. In this article, we evaluate the impact of an educational innovation project, named TrivialCV, in terms of student motivation, engagement, and learning outcomes. We analyze the impact of two types of activities: multiplayer team-based competitions created for delivery during a live class session and single-player competitions created to be played asynchronously from home. We deployed these activities in two different computer engineering courses (programming fundamentals and operating systems) and used questionnaires, grades, and activity tracking in the virtual campus to evaluate their impact. After the analysis, we can assert that the use of TrivialCV activities was useful for providing additional motivation to the students and improving their engagement with the courses in which they were deployed. TrivialCV activities were very well received by the students, who considered them fun, engaging, and useful.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Making students become intrinsically motivated to participate in daily class activities is an open challenge that has been addressed in different ways. In this article, we evaluate the impact of an educational innovation project, named TrivialCV, in terms of student motivation, engagement, and learning outcomes. We analyze the impact of two types of activities: multiplayer team-based competitions created for delivery during a live class session and single-player competitions created to be played asynchronously from home. We deployed these activities in two different computer engineering courses (programming fundamentals and operating systems) and used questionnaires, grades, and activity tracking in the virtual campus to evaluate their impact. After the analysis, we can assert that the use of TrivialCV activities was useful for providing additional motivation to the students and improving their engagement with the courses in which they were deployed. TrivialCV activities were very well received by the students, who considered them fun, engaging, and useful.
Guasch, Daniel; Martín-Escalona, Israel; Macías, José A; Francisco, Virginia; Hervás, Raquel; Moreno, Lourdes; Bautista, Susana
Design and evaluation of ECO: an augmentative and alternative communication tool Journal Article
In: Universal Access in the Information Society, vol. 21, iss. 4, pp. 827-849, 2022, ISSN: 1615-5297.
@article{guasch2022design,
title = {Design and evaluation of ECO: an augmentative and alternative communication tool},
author = {Daniel Guasch and Israel Mart\'{i}n-Escalona and Jos\'{e} A Mac\'{i}as and Virginia Francisco and Raquel Herv\'{a}s and Lourdes Moreno and Susana Bautista},
url = {https://link.springer.com/article/10.1007/s10209-021-00819-x},
doi = {10.1007/s10209-021-00819-x},
issn = {1615-5297},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Universal Access in the Information Society},
volume = {21},
issue = {4},
pages = {827-849},
publisher = {Springer},
abstract = {Current technology provides new challenges to improve skills on people with special necessities. In fact, persons with communications needs can take advantage of new devices and mobile applications to interact and communicate easily and in the most straightforward way. Augmentative and alternative communication (AAC) systems are oriented to users who cannot use natural language due to temporary or permanent impairments, providing an alternative to natural language for communication. In this paper, we present design guidelines for easy communication application (ECO), an AAC tool designed with a user-centered design approach to make functional communication easier for individuals with complex communication needs. ECO tool has two well-defined modules: the Communication User and the Communication Manager. The former is thought as an AAC tool, while the Communication Manager module provides a way to edit the content and fit the dynamics of use and application design to the user’s interests. In addition, we present an evaluation of the ECO tool from two different perspectives. On the one hand, we have achieved a heuristic-based expert evaluation in order to analyze the functionality corresponding to the Communication Manager module of the tool, in order to check main accessibility requirements and improve functionality accordingly. On the other hand, we have evaluated both the communication manager and communication user modules in a real context, carrying out a qualitative evaluation with final users and their therapists to check whether the tool is useful in concrete daily scenarios. Results corroborate research questions, demonstrating that ECO meets the most important accessibility requirements and it is highly valued by experts and end-users.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Current technology provides new challenges to improve skills on people with special necessities. In fact, persons with communications needs can take advantage of new devices and mobile applications to interact and communicate easily and in the most straightforward way. Augmentative and alternative communication (AAC) systems are oriented to users who cannot use natural language due to temporary or permanent impairments, providing an alternative to natural language for communication. In this paper, we present design guidelines for easy communication application (ECO), an AAC tool designed with a user-centered design approach to make functional communication easier for individuals with complex communication needs. ECO tool has two well-defined modules: the Communication User and the Communication Manager. The former is thought as an AAC tool, while the Communication Manager module provides a way to edit the content and fit the dynamics of use and application design to the user’s interests. In addition, we present an evaluation of the ECO tool from two different perspectives. On the one hand, we have achieved a heuristic-based expert evaluation in order to analyze the functionality corresponding to the Communication Manager module of the tool, in order to check main accessibility requirements and improve functionality accordingly. On the other hand, we have evaluated both the communication manager and communication user modules in a real context, carrying out a qualitative evaluation with final users and their therapists to check whether the tool is useful in concrete daily scenarios. Results corroborate research questions, demonstrating that ECO meets the most important accessibility requirements and it is highly valued by experts and end-users.
Gómez, Marco Antonio; Gómez, Pedro Pablo; Hervás, Raquel; Rosa, Fernando; Ruiz, Rafael; Soria, David; Mirones, José María
Implementación inicial del sistema de información docente de la Facultad de Informática Journal Article
In: 2022.
@article{gomez2022implementacion,
title = {Implementaci\'{o}n inicial del sistema de informaci\'{o}n docente de la Facultad de Inform\'{a}tica},
author = {Marco Antonio G\'{o}mez and Pedro Pablo G\'{o}mez and Raquel Herv\'{a}s and Fernando Rosa and Rafael Ruiz and David Soria and Jos\'{e} Mar\'{i}a Mirones},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2021
Gómez, Marco Antonio; Gómez, Pedro Pablo; Hervas, Raquel; Vázquez, José Luis; Martínez, Ivan; Rosa, Fernando; Ruiz, Rafael; Mirones, José María; Ventura, Irene Josefina; Soria, David
Renovación del sistema de información docente de la Facultad de Informática Journal Article
In: 2021.
@article{gomez2021renovacion,
title = {Renovaci\'{o}n del sistema de informaci\'{o}n docente de la Facultad de Inform\'{a}tica},
author = {Marco Antonio G\'{o}mez and Pedro Pablo G\'{o}mez and Raquel Hervas and Jos\'{e} Luis V\'{a}zquez and Ivan Mart\'{i}nez and Fernando Rosa and Rafael Ruiz and Jos\'{e} Mar\'{i}a Mirones and Irene Josefina Ventura and David Soria},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Julca, Frank; Méndez, Gonzalo; Hervás, Raquel
An Internal Model for Characters in Virtual Environments Book Chapter
In: Virtual Reality Designs, Chapter 5, CRC Press, Boca Raton, 1st, 2020, ISSN: 9781003019589.
@inbook{757,
title = {An Internal Model for Characters in Virtual Environments},
author = {Frank Julca and Gonzalo M\'{e}ndez and Raquel Herv\'{a}s},
url = {https://www.taylorfrancis.com/books/e/9781003019589/chapters/10.1201/9781003019589-5},
doi = {10.1201/9781003019589-5},
issn = {9781003019589},
year = {2020},
date = {2020-01-01},
booktitle = {Virtual Reality Designs},
publisher = {CRC Press},
address = {Boca Raton},
edition = {1st},
chapter = {5},
organization = {CRC Press},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Hervás, Raquel; Bautista, Susana; Méndez, Gonzalo; Galván, Paloma; Gervás, Pablo
Predictive Composition of Pictogram Messages for Users with Autism Journal Article
In: Journal of Ambient Intelligence and Humanized Computing, 2020.
@article{756,
title = {Predictive Composition of Pictogram Messages for Users with Autism},
author = {Raquel Herv\'{a}s and Susana Bautista and Gonzalo M\'{e}ndez and Paloma Galv\'{a}n and Pablo Gerv\'{a}s},
doi = {10.1007/s12652-020-01925-z},
year = {2020},
date = {2020-01-01},
journal = {Journal of Ambient Intelligence and Humanized Computing},
abstract = {Communication is a basic need for every person. However, there are many people who present disabilities that prevent communication through natural language. Augmentative and Alternative Communication (AAC) systems, including those based on pictograms, attempt to facilitate the communication for people with this kind of difficulties. In this paper we present PictoEditor, an Augmentative and Alternative Communication application for the composition of pictogram messages for users with autism that incorporates prediction functionalities. Although such functionalities have been widely studied in text-based Augmentative and Alternative Communication tools, they have not been applied to pictogram based ones. The results show that prediction based on frequency of use of specific pictograms improves the immediate availability of the desired pictograms, but the improvement with prediction based on sequencing of pseudo-syntactic types of pictogram is not as clear.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Communication is a basic need for every person. However, there are many people who present disabilities that prevent communication through natural language. Augmentative and Alternative Communication (AAC) systems, including those based on pictograms, attempt to facilitate the communication for people with this kind of difficulties. In this paper we present PictoEditor, an Augmentative and Alternative Communication application for the composition of pictogram messages for users with autism that incorporates prediction functionalities. Although such functionalities have been widely studied in text-based Augmentative and Alternative Communication tools, they have not been applied to pictogram based ones. The results show that prediction based on frequency of use of specific pictograms improves the immediate availability of the desired pictograms, but the improvement with prediction based on sequencing of pseudo-syntactic types of pictogram is not as clear.
2019
Hervás, Raquel; Francisco, Virginia; Méndez, Gonzalo; Bautista, Susana
A User-Centred Methodology for the Development of Computer-Based Assistive Technologies for Individuals with Autism Proceedings Article
In: Lamas, David; Loizides, Fernando; Nacke, Lennart; Petrie, Helen; Winckler, Marco; Zaphiris, Panayiotis (Ed.): 17th IFIP TC.13 International Conference on Human-Computer Interaction (INTERACT 2019), pp. 85–106, Springer Springer, Paphos, Cyprus, 2019, ISBN: 978-3-030-29381-9.
@inproceedings{734,
title = {A User-Centred Methodology for the Development of Computer-Based Assistive Technologies for Individuals with Autism},
author = {Raquel Herv\'{a}s and Virginia Francisco and Gonzalo M\'{e}ndez and Susana Bautista},
editor = {David Lamas and Fernando Loizides and Lennart Nacke and Helen Petrie and Marco Winckler and Panayiotis Zaphiris},
url = {https://link.springer.com/chapter/10.1007/978-3-030-29381-9_6},
doi = {https://doi.org/10.1007/978-3-030-29381-9_6},
isbn = {978-3-030-29381-9},
year = {2019},
date = {2019-08-23},
urldate = {2019-08-23},
booktitle = {17th IFIP TC.13 International Conference on Human-Computer Interaction (INTERACT 2019)},
volume = {11746},
pages = {85--106},
publisher = {Springer},
address = {Paphos, Cyprus},
organization = {Springer},
abstract = {The design and development of computer assistive technolo-gies must be tied to the needs and goals of end users and must takeinto account their capabilities and preferences. In this paper, we presentMeDeC@, a Methodology for the Development of Computer AssistiveTechnologies for people with Autism Spectrum Disorders (ASD), whichrelies heavily in our experience working with end users with ASD. Theaim of this methodology is not to design for a broad group of users, butto design highly customizable tools so that they can be easily adaptedto specific situations and small user groups. We also present two applications developed using MeDeC@ in order to test its suitability: Emo-Traductor, a web application for emotion recognition for people withAsperger Syndrome, and ReadIt, a web browser plug-in to help peoplewith ASD with written language understanding difficulties to navigatethe Internet. The results of our evaluation with end users show thatthe use of MeDeC@ helps developers to successfully design computerassistive technologies taking into account the special requirements andscenarios that arise when developing this kind of assistive applications.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The design and development of computer assistive technolo-gies must be tied to the needs and goals of end users and must takeinto account their capabilities and preferences. In this paper, we presentMeDeC@, a Methodology for the Development of Computer AssistiveTechnologies for people with Autism Spectrum Disorders (ASD), whichrelies heavily in our experience working with end users with ASD. Theaim of this methodology is not to design for a broad group of users, butto design highly customizable tools so that they can be easily adaptedto specific situations and small user groups. We also present two applications developed using MeDeC@ in order to test its suitability: Emo-Traductor, a web application for emotion recognition for people withAsperger Syndrome, and ReadIt, a web browser plug-in to help peoplewith ASD with written language understanding difficulties to navigatethe Internet. The results of our evaluation with end users show thatthe use of MeDeC@ helps developers to successfully design computerassistive technologies taking into account the special requirements andscenarios that arise when developing this kind of assistive applications.
Martins, Pedro; Oliveira, Hugo Gonçalo; Gonçalves, Joao Carlos; Cruz, Antonio; Cardoso, Amílcar; Znidarzic, Martin; Lavrac, Nada; Linkola, Simo M.; Toivonen, Hannu; Hervás, Raquel; Méndez, Gonzalo; Gervás, Pablo
Computational Creativity Infrastructure for Online Software Composition: A Conceptual Blending Use Case Journal Article
In: IBM Journal of Research and Development, pp. 1-1, 2019, ISSN: 0018-8646.
@article{723,
title = {Computational Creativity Infrastructure for Online Software Composition: A Conceptual Blending Use Case},
author = {Pedro Martins and Hugo Gon\c{c}alo Oliveira and Joao Carlos Gon\c{c}alves and Antonio Cruz and Am\'{i}lcar Cardoso and Martin Znidarzic and Nada Lavrac and Simo M. Linkola and Hannu Toivonen and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez and Pablo Gerv\'{a}s},
url = {https://ieeexplore.ieee.org/document/8637717},
doi = {10.1147/JRD.2019.2898417},
issn = {0018-8646},
year = {2019},
date = {2019-01-01},
journal = {IBM Journal of Research and Development},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Méndez, Gonzalo; Hervás, Raquel; Gervás, Pablo; Martín, Alejandro; Julca, Frank
Dynamic Emphatical Narration for Reduced Authorial Burden and Increased User Freedom in Interactive Storytelling Journal Article
In: Connection Science, vol. 31, no. 1, pp. 33-59, 2019, ISSN: 0954-0091.
@article{699,
title = {Dynamic Emphatical Narration for Reduced Authorial Burden and Increased User Freedom in Interactive Storytelling},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Alejandro Mart\'{i}n and Frank Julca},
doi = {10.1080/09540091.2018.1454891},
issn = {0954-0091},
year = {2019},
date = {2019-01-01},
journal = {Connection Science},
volume = {31},
number = {1},
pages = {33-59},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xiao, Ping; Toivonen, Hannu; Gross, Oskar; Cardoso, Amílcar; Correia, João; Machado, Penousal; Martins, Pedro; Oliveira, Hugo Gonçalo; Sharma, Rahul; Pinto, Alexandre Miguel; Díaz, Alberto; Francisco, Virginia; Gervás, Pablo; Hervás, Raquel; León, Carlos; Forth, Jamie; Purver, Matthew; Wiggins, Geraint A.; Miljković, Dragana; Podpečan, Vid; Pollak, Senja; Kralj, Jan; Żnidaršič, Martin; Bohanec, Marko; Lavrac, Nada; Urbančič, Tanja; Velde, Frank Van Der; Battersby, Stuart
Conceptual Representations for Computational Concept Creation Journal Article
In: ACM Comput. Surv., vol. 52, no. 1, pp. 9:1–9:33, 2019, ISSN: 0360-0300.
@article{725,
title = {Conceptual Representations for Computational Concept Creation},
author = {Ping Xiao and Hannu Toivonen and Oskar Gross and Am\'{i}lcar Cardoso and Jo\~{a}o Correia and Penousal Machado and Pedro Martins and Hugo Gon\c{c}alo Oliveira and Rahul Sharma and Alexandre Miguel Pinto and Alberto D\'{i}az and Virginia Francisco and Pablo Gerv\'{a}s and Raquel Herv\'{a}s and Carlos Le\'{o}n and Jamie Forth and Matthew Purver and Geraint A. Wiggins and Dragana Miljkovi\'{c} and Vid Podpe\v{c}an and Senja Pollak and Jan Kralj and Martin \.{Z}nidar\v{s}i\v{c} and Marko Bohanec and Nada Lavrac and Tanja Urban\v{c}i\v{c} and Frank Van Der Velde and Stuart Battersby},
url = {https://dl.acm.org/doi/10.1145/3186729},
doi = {10.1145/3186729},
issn = {0360-0300},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
journal = {ACM Comput. Surv.},
volume = {52},
number = {1},
pages = {9:1\textendash9:33},
abstract = {Computational creativity seeks to understand computational mechanisms that can be characterized as creative. The creation of new concepts is a central challenge for any creative system. In this article, we outline different approaches to computational concept creation and then review conceptual representations relevant to concept creation, and therefore to computational creativity. The conceptual representations are organized in accordance with two important perspectives on the distinctions between them. One distinction is between symbolic, spatial and connectionist representations. The other is between descriptive and procedural representations. Additionally, conceptual representations used in particular creative domains, such as language, music, image and emotion, are reviewed separately. For every representation reviewed, we cover the inference it affords, the computational means of building it, and its application in concept creation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Computational creativity seeks to understand computational mechanisms that can be characterized as creative. The creation of new concepts is a central challenge for any creative system. In this article, we outline different approaches to computational concept creation and then review conceptual representations relevant to concept creation, and therefore to computational creativity. The conceptual representations are organized in accordance with two important perspectives on the distinctions between them. One distinction is between symbolic, spatial and connectionist representations. The other is between descriptive and procedural representations. Additionally, conceptual representations used in particular creative domains, such as language, music, image and emotion, are reviewed separately. For every representation reviewed, we cover the inference it affords, the computational means of building it, and its application in concept creation.
Guasch, Daniel; Martín-Escalona, Israel; Macías, José A.; Moreno, Lourdes; Hervás, Raquel; Bautista, Susana
Expert-based Assessment of an Augmentative and Alternative Communication Tool Proceedings Article
In: XX International Conference on Human Computer Interaction (Interacción 2019), ACM Digital Library ACM Digital Library, Donostia, Gipuzkoa, Spain, 2019.
@inproceedings{751,
title = {Expert-based Assessment of an Augmentative and Alternative Communication Tool},
author = {Daniel Guasch and Israel Mart\'{i}n-Escalona and Jos\'{e} A. Mac\'{i}as and Lourdes Moreno and Raquel Herv\'{a}s and Susana Bautista},
url = {https://dl.acm.org/citation.cfm?id=3335631},
doi = {doi.org/10.1145/3335595.3335631},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
booktitle = {XX International Conference on Human Computer Interaction (Interacci\'{o}n 2019)},
publisher = {ACM Digital Library},
address = {Donostia, Gipuzkoa, Spain},
organization = {ACM Digital Library},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Méndez, Gonzalo; Hervás, Raquel; Gervás, Pablo; Rosa, Ricardo; Ruiz, Daniel
Adapting Descriptions of People to the Point of View of a Moving Observer Proceedings Article
In: 11th International Conference on Natural Languaje Generation (INLG), ACL ACL, Tilburg, The Netherlands, 2018.
@inproceedings{715,
title = {Adapting Descriptions of People to the Point of View of a Moving Observer},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Ricardo Rosa and Daniel Ruiz},
url = {https://www.aclweb.org/anthology/W18-6540},
doi = {http://dx.doi.org/10.18653/v1/W18-6540},
year = {2018},
date = {2018-11-01},
urldate = {2018-11-01},
booktitle = {11th International Conference on Natural Languaje Generation (INLG)},
publisher = {ACL},
address = {Tilburg, The Netherlands},
organization = {ACL},
abstract = {This paper addresses the task of generating descriptions of people for an observer that is moving within a scene. As the observer moves, the descriptions of the people around him also change. A referring expression generation algorithm adapted to this task needs to continuously monitor the changes in the field of view of the observer, his relative position to the people being described, and the relative position of these people to any landmarks around them, and to take these changes into account in the referring expressions generated. This task presents two advantages: many of the mechanisms already available for static contexts may be applied with small adaptations, and it introduces the concept of changing conditions into the task of referring expression generation. In this paper we describe the design of an algorithm that takes these aspects into account in order to create descriptions of people within a 3D virtual environment. The evaluation of this algorithm has shown that, by changing the descriptions in real time according to the observers point of view, they are able to identify the described person quickly and effectively.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper addresses the task of generating descriptions of people for an observer that is moving within a scene. As the observer moves, the descriptions of the people around him also change. A referring expression generation algorithm adapted to this task needs to continuously monitor the changes in the field of view of the observer, his relative position to the people being described, and the relative position of these people to any landmarks around them, and to take these changes into account in the referring expressions generated. This task presents two advantages: many of the mechanisms already available for static contexts may be applied with small adaptations, and it introduces the concept of changing conditions into the task of referring expression generation. In this paper we describe the design of an algorithm that takes these aspects into account in order to create descriptions of people within a 3D virtual environment. The evaluation of this algorithm has shown that, by changing the descriptions in real time according to the observers point of view, they are able to identify the described person quickly and effectively.
Francisco, Virginia; Hervás, Raquel; Méndez, Gonzalo; Galván, Paloma
In: Frontiers in Psychology, vol. 9, 2018, ISSN: 1664-1078.
@article{714,
title = {Exploring the Potential of Concept Associations for the Creative Generation of Linguistic Artifacts: a Case Study with Riddles and Rhetorical Figures},
author = {Virginia Francisco and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez and Paloma Galv\'{a}n},
url = {https://www.frontiersin.org/articles/10.3389/fpsyg.2018.01792},
doi = {10.3389/fpsyg.2018.01792},
issn = {1664-1078},
year = {2018},
date = {2018-09-01},
journal = {Frontiers in Psychology},
volume = {9},
chapter = {1792},
abstract = {Automatic generation of linguistic artifacts is a problem that has been sporadically tackled over the years. The main goal of this paper is to explore how concept associations can be useful from a computational creativity point of view to generate some of these artifacts. We present an approach where finding associations between concepts that would not usually be considered as related (for example life and politics or diamond and concrete) could be the seed for the generation of creative and surprising linguistic artifacts such as rhetorical figures (life is like politics) and riddles (what is as hard as concrete?). The quality and appropriateness of the generated figures and riddles has been evaluated using human evaluators, and the results show that the concept associations obtained are useful for creating these kinds of creative artifacts.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Automatic generation of linguistic artifacts is a problem that has been sporadically tackled over the years. The main goal of this paper is to explore how concept associations can be useful from a computational creativity point of view to generate some of these artifacts. We present an approach where finding associations between concepts that would not usually be considered as related (for example life and politics or diamond and concrete) could be the seed for the generation of creative and surprising linguistic artifacts such as rhetorical figures (life is like politics) and riddles (what is as hard as concrete?). The quality and appropriateness of the generated figures and riddles has been evaluated using human evaluators, and the results show that the concept associations obtained are useful for creating these kinds of creative artifacts.
Martín, Alejandro; Hervás, Raquel; Méndez, Gonzalo; Bautista, Susana
PICTAR: Una herramienta de elaboración de contenido para personas con TEA basada en la traducción de texto a pictogramas Proceedings Article
In: XIX International Conference on Human-Computer Interaction (Interacción 2018), Palma de Mallorca, Spain, 2018.
@inproceedings{712,
title = {PICTAR: Una herramienta de elaboraci\'{o}n de contenido para personas con TEA basada en la traducci\'{o}n de texto a pictogramas},
author = {Alejandro Mart\'{i}n and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez and Susana Bautista},
url = {https://docta.ucm.es/bitstreams/f043e925-f4dc-439a-bf8f-3d8df91f82fc/download},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {XIX International Conference on Human-Computer Interaction (Interacci\'{o}n 2018)},
address = {Palma de Mallorca, Spain},
abstract = {Los avances actuales en el campo de las TICs han permitido un importante impulso en el desarrollo de los Sistemas Aumentativos y Alternativos de Comunicacion (SAACs), tan necesarios para que las personas con discapacidad puedan comunicarse con su entorno. Dichos sistemas permiten atraer la atencion de este colectivo mediante la presentacion de imagenes y sonidos de una manera estimulante. La adopcion de estos SAACs por parte de personas con dificultades en la comunicacion potencia el desarrollo del lenguaje sin suponer ningun impedimento para el desarrollo del habla, sino al contrario. En concreto, para las personas con TEA (Trastorno del Espectro Autista), es fundamental tener formas alternativas de recibir la informacion de su contexto mediante refuerzos visuales, auditivos o mixtos.
En este trabajo se presenta PICTAR, una aplicacion orientada a personas con TEA, que facilita el trabajo con pictogramas y la elaboracion de materiales a partir de estos en el ambito de la educacion especial. Se ha concebido como una aplicacion web, haciendola accesible desde cualquier parte e intentando ponerla al alcance del mayor numero de usuarios posible. Esta constituida por una herramienta de edicion que permite crear materiales basados en pictogramas de una manera comoda y sencilla, y ademas incluye un servicio de traduccion de texto a pictogramas.
El desarrollo de este proyecto se ha realizado en estrecha colaboracion con asociaciones y centros de educacion especial, de cara a resolver los problemas que encuentran a la hora de trabajar con pictogramas de la manera mas adaptada a sus necesidades que sea posible. Estas entidades han participado desde la toma de requisitos hasta las evaluaciones finales con profesionales y usuarios con TEA.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Los avances actuales en el campo de las TICs han permitido un importante impulso en el desarrollo de los Sistemas Aumentativos y Alternativos de Comunicacion (SAACs), tan necesarios para que las personas con discapacidad puedan comunicarse con su entorno. Dichos sistemas permiten atraer la atencion de este colectivo mediante la presentacion de imagenes y sonidos de una manera estimulante. La adopcion de estos SAACs por parte de personas con dificultades en la comunicacion potencia el desarrollo del lenguaje sin suponer ningun impedimento para el desarrollo del habla, sino al contrario. En concreto, para las personas con TEA (Trastorno del Espectro Autista), es fundamental tener formas alternativas de recibir la informacion de su contexto mediante refuerzos visuales, auditivos o mixtos.
En este trabajo se presenta PICTAR, una aplicacion orientada a personas con TEA, que facilita el trabajo con pictogramas y la elaboracion de materiales a partir de estos en el ambito de la educacion especial. Se ha concebido como una aplicacion web, haciendola accesible desde cualquier parte e intentando ponerla al alcance del mayor numero de usuarios posible. Esta constituida por una herramienta de edicion que permite crear materiales basados en pictogramas de una manera comoda y sencilla, y ademas incluye un servicio de traduccion de texto a pictogramas.
El desarrollo de este proyecto se ha realizado en estrecha colaboracion con asociaciones y centros de educacion especial, de cara a resolver los problemas que encuentran a la hora de trabajar con pictogramas de la manera mas adaptada a sus necesidades que sea posible. Estas entidades han participado desde la toma de requisitos hasta las evaluaciones finales con profesionales y usuarios con TEA.
En este trabajo se presenta PICTAR, una aplicacion orientada a personas con TEA, que facilita el trabajo con pictogramas y la elaboracion de materiales a partir de estos en el ambito de la educacion especial. Se ha concebido como una aplicacion web, haciendola accesible desde cualquier parte e intentando ponerla al alcance del mayor numero de usuarios posible. Esta constituida por una herramienta de edicion que permite crear materiales basados en pictogramas de una manera comoda y sencilla, y ademas incluye un servicio de traduccion de texto a pictogramas.
El desarrollo de este proyecto se ha realizado en estrecha colaboracion con asociaciones y centros de educacion especial, de cara a resolver los problemas que encuentran a la hora de trabajar con pictogramas de la manera mas adaptada a sus necesidades que sea posible. Estas entidades han participado desde la toma de requisitos hasta las evaluaciones finales con profesionales y usuarios con TEA.
Méndez, Gonzalo; Hervás, Raquel; Bautista, Susana; Galván, Paloma
PictoEditor: un editor predictivo basado en pictogramas para facilitar la interacción con personas con discapacidad Proceedings Article
In: XIX International Conference on Human-Computer Interaction (Interacción 2018), Palma de Mallorca, Spain, 2018.
@inproceedings{711,
title = {PictoEditor: un editor predictivo basado en pictogramas para facilitar la interacci\'{o}n con personas con discapacidad},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Susana Bautista and Paloma Galv\'{a}n},
url = {https://www.researchgate.net/publication/326089708_PictoEditor_un_editor_predictivo_basado_en_pictogramas_para_facilitar_la_interaccion_con_personas_con_discapacidad},
year = {2018},
date = {2018-09-01},
urldate = {2018-09-01},
booktitle = {XIX International Conference on Human-Computer Interaction (Interacci\'{o}n 2018)},
address = {Palma de Mallorca, Spain},
abstract = {La comunicaci\'{o}n es una necesidad b\'{a}sica de las personas, pero existen numerosas discapacidades que dicultan las posibilidades de comunicaci\'{o}n mediante lenguaje natural. Para las personas que padecen alguna de estas discapacidades, los Sistemas Aumentativos y Alternativos de Comunicaci\'{o}n (SAACs), incluyendo los que se ba-san en el uso de pictogramas, constituyen un medio para paliar estasdificultades de comunicaci\'{o}n. En este trabajo se presenta PictoEditor, un SAAC para la composici\'{o}n de mensajes con pictogramas con ayuda de un algoritmo de predicci\'{o}n que facilita la selecci\'{o}n e los pictogramas a utilizar en los mensajes. Tras realizar una serie de evaluaciones preliminares, los resultados muestran que el algoritmo de predicci\'{o}n facilita la labor de edici\'{o}n de mensajes para los educadores de ni\~{n}os con Trastornos del Espectro del Autismo.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
La comunicación es una necesidad básica de las personas, pero existen numerosas discapacidades que dicultan las posibilidades de comunicación mediante lenguaje natural. Para las personas que padecen alguna de estas discapacidades, los Sistemas Aumentativos y Alternativos de Comunicación (SAACs), incluyendo los que se ba-san en el uso de pictogramas, constituyen un medio para paliar estasdificultades de comunicación. En este trabajo se presenta PictoEditor, un SAAC para la composición de mensajes con pictogramas con ayuda de un algoritmo de predicción que facilita la selección e los pictogramas a utilizar en los mensajes. Tras realizar una serie de evaluaciones preliminares, los resultados muestran que el algoritmo de predicción facilita la labor de edición de mensajes para los educadores de niños con Trastornos del Espectro del Autismo.
Bautista, Susana; Hervás, Raquel; Gervás, Pablo; Bagó, Axel; García-Ortiz, Javier
Taking text simplification to the user: integrating automated modules into a web browser Proceedings Article
In: The 8th International Conference on Software Development and Technologies for Enchancing Accessibility and Fighting Info-exclusion (DSAI 2018), 2018.
@inproceedings{710,
title = {Taking text simplification to the user: integrating automated modules into a web browser},
author = {Susana Bautista and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Axel Bag\'{o} and Javier Garc\'{i}a-Ortiz},
doi = {doi.org/10.1145/3218585.3218591},
year = {2018},
date = {2018-06-01},
urldate = {2018-06-01},
booktitle = {The 8th International Conference on Software Development and Technologies for Enchancing Accessibility and Fighting Info-exclusion (DSAI 2018)},
abstract = {There are a lot of people who experience reading or writing problems. To address this challenge, there are different possible approaches can be followed: to provide technologies to ease the task of human volunteers faced with the challenge of rewriting existing texts so that poor literacy readers can read them, or to provide technologies to help poor literacy readers deal with the challenge of understanding texts that are originally beyond their reach. Following the last approach, the present paper describes the development of elementary modules useful for simplification processes and the integration of these modules into text processing applications. The text processing applications are considered into a web browser, where simplification modules are accessed as web services.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
There are a lot of people who experience reading or writing problems. To address this challenge, there are different possible approaches can be followed: to provide technologies to ease the task of human volunteers faced with the challenge of rewriting existing texts so that poor literacy readers can read them, or to provide technologies to help poor literacy readers deal with the challenge of understanding texts that are originally beyond their reach. Following the last approach, the present paper describes the development of elementary modules useful for simplification processes and the integration of these modules into text processing applications. The text processing applications are considered into a web browser, where simplification modules are accessed as web services.
Merino, Paloma Gutiérrez; Suárez, Gema Eugercios; Popova, Elena Kaloyanova; Francisco, Virginia; Hervás, Raquel
EmoTraductor: Análisis Emocional para la Inclusión Digital Proceedings Article
In: IV Congreso Internacional Universidad y Discapacidad (CIUD 2018), Fundación ONCE Fundación ONCE, Madrid, Spain, 2018.
@inproceedings{735,
title = {EmoTraductor: An\'{a}lisis Emocional para la Inclusi\'{o}n Digital},
author = {Paloma Guti\'{e}rrez Merino and Gema Eugercios Su\'{a}rez and Elena Kaloyanova Popova and Virginia Francisco and Raquel Herv\'{a}s},
url = {https://ciud23.fundaciononce.es/sites/default/files/2023-05/libro-de-actas-iv-congreso-universidad-y-discapacidad_0.pdf},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
booktitle = {IV Congreso Internacional Universidad y Discapacidad (CIUD 2018)},
publisher = {Fundaci\'{o}n ONCE},
address = {Madrid, Spain},
organization = {Fundaci\'{o}n ONCE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2017
Méndez, Gonzalo; Hervás, Raquel; Bautista, Susana; Rabadán, Adrián; Rodríguez-Ferreira, Teresa
Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images Proceedings Article
In: International Natural Language Generation Conference (INLG2017), Santiago de Compostela, Spain, 2017.
@inproceedings{681,
title = {Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Susana Bautista and Adri\'{a}n Rabad\'{a}n and Teresa Rodr\'{i}guez-Ferreira},
url = {https://www.aclweb.org/anthology/W17-3507},
doi = {http://dx.doi.org/10.18653/v1/W17-3507},
year = {2017},
date = {2017-09-01},
urldate = {2017-09-01},
booktitle = {International Natural Language Generation Conference (INLG2017)},
address = {Santiago de Compostela, Spain},
abstract = {Describing people and characters can be very useful in different contexts, such as computational narrative or image description for the visually impaired. However, a review of the existing literature shows that the automatic generation of people descriptions has not received much attention. Our work focuses on the description of people in snapshots from a 3D environment. First, we have conducted a survey to identify the way in which people describe other people under different conditions. We have used the information extracted from this survey to design several Referring Expression Generation algorithms which produce similar results. We have evaluated these algorithms with users in order to identify which ones generate the best description for specific characters in different situations. The evaluation has shown that, in order to generate good descriptions, a combination of different algorithms has to be used depending on the features and situation of the person to be described.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Describing people and characters can be very useful in different contexts, such as computational narrative or image description for the visually impaired. However, a review of the existing literature shows that the automatic generation of people descriptions has not received much attention. Our work focuses on the description of people in snapshots from a 3D environment. First, we have conducted a survey to identify the way in which people describe other people under different conditions. We have used the information extracted from this survey to design several Referring Expression Generation algorithms which produce similar results. We have evaluated these algorithms with users in order to identify which ones generate the best description for specific characters in different situations. The evaluation has shown that, in order to generate good descriptions, a combination of different algorithms has to be used depending on the features and situation of the person to be described.
Méndez, Gonzalo; Hervás, Raquel; Gervás, Pablo; Martín, Alejandro; Julca, Frank
Exploring Creative Freedom in Real Time Story Generation Proceedings Article
In: 4th AISB Symposium on Computational Creativity (AISBCC 2017), University of Bath, UK, 2017.
@inproceedings{646,
title = {Exploring Creative Freedom in Real Time Story Generation},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Alejandro Mart\'{i}n and Frank Julca},
url = {https://www.researchgate.net/publication/316645801_Exploring_Creative_Freedom_in_Real_Time_Story_Generation},
year = {2017},
date = {2017-04-01},
urldate = {2017-04-01},
booktitle = {4th AISB Symposium on Computational Creativity (AISBCC 2017)},
address = {University of Bath, UK},
abstract = {Interactive storytelling systems have become very popular as they engage users in the creation of narrative. In order to explore a co-creation process where the final result is narrated while the user is playing, we have designed an interactive storytelling system that is able to generate a narration in real time while giving the user the possibility to decide what to do and where to go. The intended result is a tool that allows the author, the user and the system to co-create a narration giving the user, as the ultimate author of the resulting narration, the freedom to decide the course of the events. In this paper we focus on the structures that have been used to represent the stories and in the mechanisms designed to generate the narration so that a coherent and entertaining story can be presented to the user.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Interactive storytelling systems have become very popular as they engage users in the creation of narrative. In order to explore a co-creation process where the final result is narrated while the user is playing, we have designed an interactive storytelling system that is able to generate a narration in real time while giving the user the possibility to decide what to do and where to go. The intended result is a tool that allows the author, the user and the system to co-create a narration giving the user, as the ultimate author of the resulting narration, the freedom to decide the course of the events. In this paper we focus on the structures that have been used to represent the stories and in the mechanisms designed to generate the narration so that a coherent and entertaining story can be presented to the user.
Bautista, Susana; Hervás, Raquel; Gervás, Pablo; Rojo, Javier
An Approach to Treat Numerical Information in the Text Simplification Process Journal Article
In: Universal Access in the Information Society, vol. 16, no. 1, pp. 85-102, 2017, ISSN: 1615-5289.
@article{611,
title = {An Approach to Treat Numerical Information in the Text Simplification Process},
author = {Susana Bautista and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Javier Rojo},
doi = {10.1007/s10209-015-0426-z},
issn = {1615-5289},
year = {2017},
date = {2017-01-01},
journal = {Universal Access in the Information Society},
volume = {16},
number = {1},
pages = {85-102},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Oliveira, Hugo Gonçalo; Hervás, Raquel; Díaz, Alberto; Gervás, Pablo
Multilingual extension and evaluation of a poetry generator Journal Article
In: Natural Language Engineering, pp. 1–39, 2017.
@article{679,
title = {Multilingual extension and evaluation of a poetry generator},
author = {Hugo Gon\c{c}alo Oliveira and Raquel Herv\'{a}s and Alberto D\'{i}az and Pablo Gerv\'{a}s},
doi = {10.1017/S1351324917000171},
year = {2017},
date = {2017-01-01},
journal = {Natural Language Engineering},
pages = {1\textendash39},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Bautista, Susana; Hervás, Raquel; Hernández-Gil, Agustín; Martínez-Díaz, Carlos; Pascua, Sergio; Gervás, Pablo
AraTraductor: Text to Pictogram Translation using Natural Language Processing Techniques Proceedings Article
In: 18th International Conference of the Spanish Human Computer Interaction Association, 2017.
@inproceedings{680,
title = {AraTraductor: Text to Pictogram Translation using Natural Language Processing Techniques},
author = {Susana Bautista and Raquel Herv\'{a}s and Agust\'{i}n Hern\'{a}ndez-Gil and Carlos Mart\'{i}nez-D\'{i}az and Sergio Pascua and Pablo Gerv\'{a}s},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
booktitle = {18th International Conference of the Spanish Human Computer Interaction Association},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2016
Bautista, Susana; Hervás, Raquel; Gervás, Pablo
Proyecto IDiLyCo: Inclusión Digital, Lenguaje Natural y Comunicación Proceedings Article
In: CIUD, 2016.
@inproceedings{638,
title = {Proyecto IDiLyCo: Inclusi\'{o}n Digital, Lenguaje Natural y Comunicaci\'{o}n},
author = {Susana Bautista and Raquel Herv\'{a}s and Pablo Gerv\'{a}s},
year = {2016},
date = {2016-11-01},
urldate = {2016-11-01},
booktitle = {CIUD},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gervás, Pablo; Hervás, Raquel; León, Carlos; Gale, Catherine V
Annotating Musical Theatre Plots on Narrative Structure and Emotional Content Proceedings Article
In: Seventh International Workshop on Computational Models of Narrative, OpenAccess Series in Informatics OpenAccess Series in Informatics, Kravov, Poland, 2016.
@inproceedings{624,
title = {Annotating Musical Theatre Plots on Narrative Structure and Emotional Content},
author = {Pablo Gerv\'{a}s and Raquel Herv\'{a}s and Carlos Le\'{o}n and Catherine V Gale},
year = {2016},
date = {2016-07-01},
urldate = {2016-07-01},
booktitle = {Seventh International Workshop on Computational Models of Narrative},
publisher = {OpenAccess Series in Informatics},
address = {Kravov, Poland},
organization = {OpenAccess Series in Informatics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Znidarsic, Martin; Cardoso, Amílcar; Gervás, Pablo; Martins, Pedro; Hervás, Raquel; Alves, Ana Oliveira; Oliveira, Hugo Gonçalo; Xiao, Ping; Linkola, Simo; Toivonen, Hannu; Kranjc, Janez; Lavrac, Nada
Computational Creativity Infrastructure for Online Software Composition: A Conceptual Blending Use Case Proceedings Article
In: Seventh International Conference on Computational Creativity (ICCC 2016), Sony CSL Sony CSL, Paris, France, 2016.
@inproceedings{698,
title = {Computational Creativity Infrastructure for Online Software Composition: A Conceptual Blending Use Case},
author = {Martin Znidarsic and Am\'{i}lcar Cardoso and Pablo Gerv\'{a}s and Pedro Martins and Raquel Herv\'{a}s and Ana Oliveira Alves and Hugo Gon\c{c}alo Oliveira and Ping Xiao and Simo Linkola and Hannu Toivonen and Janez Kranjc and Nada Lavrac},
year = {2016},
date = {2016-06-01},
urldate = {2016-06-01},
booktitle = {Seventh International Conference on Computational Creativity (ICCC 2016)},
publisher = {Sony CSL},
address = {Paris, France},
organization = {Sony CSL},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Galván, Paloma; Francisco, Virginia; Hervás, Raquel; Méndez, Gonzalo; Gervás, Pablo
Exploring the Role of Word Associations in the Construction of Rhetorical Figures Proceedings Article
In: 7th International Conference on Computational Creativity (ICCC 2016), pp. 222-229, Paris, France, 2016.
@inproceedings{625,
title = {Exploring the Role of Word Associations in the Construction of Rhetorical Figures},
author = {Paloma Galv\'{a}n and Virginia Francisco and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez and Pablo Gerv\'{a}s},
url = {https://www.computationalcreativity.net/iccc2016/wp-content/uploads/2016/01/Exploring-the-Role-ofWord-Associations-in-the-Construction-of-Rhetorical-Figures.pdf},
year = {2016},
date = {2016-06-01},
urldate = {2016-06-01},
booktitle = {7th International Conference on Computational Creativity (ICCC 2016)},
pages = {222-229},
address = {Paris, France},
abstract = {Figurative language is a fundamental characteristic of elaborate forms of linguistic communication. We currently have very poor models of howfigurative language may be constructed in computational terms. The overall aim is to identify possible regularities, intuitions or heuristics that may at a later stage be employed to drive a text generator that is capable of using this type of rhetorical figure.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Figurative language is a fundamental characteristic of elaborate forms of linguistic communication. We currently have very poor models of howfigurative language may be constructed in computational terms. The overall aim is to identify possible regularities, intuitions or heuristics that may at a later stage be employed to drive a text generator that is capable of using this type of rhetorical figure.
Bautista, Susana; Hervás, Raquel; Gervás, Pablo
Automatic Simplification of Numerical Expressions using Fuzzy Logic Proceedings Article
In: XVIII Congreso Español sobre Tecnologías y Lógica Fuzzy. ESTYLF 2016, Donostia-San Sebastián, Spain, 2016.
@inproceedings{622,
title = {Automatic Simplification of Numerical Expressions using Fuzzy Logic},
author = {Susana Bautista and Raquel Herv\'{a}s and Pablo Gerv\'{a}s},
year = {2016},
date = {2016-05-01},
urldate = {2016-05-01},
booktitle = {XVIII Congreso Espa\~{n}ol sobre Tecnolog\'{i}as y L\'{o}gica Fuzzy. ESTYLF 2016},
address = {Donostia-San Sebasti\'{a}n, Spain},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rodríguez-Ferreira, Teresa; Rabadán, Adrián; Hervás, Raquel; Díaz, Alberto
Improving Information Extraction from Wikipedia Texts using Basic English Proceedings Article
In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), European Language Resources Association (ELRA) European Language Resources Association (ELRA), Paris, France, 2016, ISBN: 978-2-9517408-9-1.
@inproceedings{634,
title = {Improving Information Extraction from Wikipedia Texts using Basic English},
author = {Teresa Rodr\'{i}guez-Ferreira and Adri\'{a}n Rabad\'{a}n and Raquel Herv\'{a}s and Alberto D\'{i}az},
isbn = {978-2-9517408-9-1},
year = {2016},
date = {2016-05-01},
urldate = {2016-05-01},
booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
publisher = {European Language Resources Association (ELRA)},
address = {Paris, France},
organization = {European Language Resources Association (ELRA)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Galván, Paloma; Francisco, Virginia; Hervás, Raquel; Méndez, Gonzalo
Riddle Generation using Word Associations Proceedings Article
In: Nicoletta Choukri Calzolari, Khalid Declerck (Ed.): Language Resources and Evaluation Conference (LREC 2016), pp. 2407-2412, European Language Resources Association (ELRA) Portoroz, Slovenia, 2016.
@inproceedings{618,
title = {Riddle Generation using Word Associations},
author = {Paloma Galv\'{a}n and Virginia Francisco and Raquel Herv\'{a}s and Gonzalo M\'{e}ndez},
editor = {Calzolari, Nicoletta
Choukri, Khalid
Declerck, Thierry
Goggi, Sara
Grobelnik, Marko
Maegaard, Bente
Mariani, Joseph
Mazo, Helene
Moreno, Asuncion
Odijk, Jan
Piperidis, Stelios},
url = {https://www.aclweb.org/anthology/L16-1381},
year = {2016},
date = {2016-05-01},
urldate = {2016-05-01},
booktitle = {Language Resources and Evaluation Conference (LREC 2016)},
pages = {2407-2412},
address = {Portoroz, Slovenia},
organization = {European Language Resources Association (ELRA)},
abstract = {In knowledge bases where concepts have associated properties, there is a large amount of comparative information that is implicitly encoded in the values of the properties these concepts share. Although there have been previous approaches to generating riddles, none of them seem to take advantage of structured information stored in knowledge bases such as Thesaurus Rex, which organizes concepts according to the fine grained ad-hoc categories they are placed into by speakers in everyday language, along with associated properties or modifiers. Taking advantage of these shared properties, we have developed a riddle generator that creates riddles about concepts represented as common nouns. The base of these riddles are comparisons between the target concept and other entities that share some of its properties. In this paper, we describe the process we have followed to generate the riddles starting from the target concept and we show the results of the first evaluation we have carried out to test the quality of the resulting riddles.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In knowledge bases where concepts have associated properties, there is a large amount of comparative information that is implicitly encoded in the values of the properties these concepts share. Although there have been previous approaches to generating riddles, none of them seem to take advantage of structured information stored in knowledge bases such as Thesaurus Rex, which organizes concepts according to the fine grained ad-hoc categories they are placed into by speakers in everyday language, along with associated properties or modifiers. Taking advantage of these shared properties, we have developed a riddle generator that creates riddles about concepts represented as common nouns. The base of these riddles are comparisons between the target concept and other entities that share some of its properties. In this paper, we describe the process we have followed to generate the riddles starting from the target concept and we show the results of the first evaluation we have carried out to test the quality of the resulting riddles.
Méndez, Gonzalo; Hervás, Raquel; Gervás, Pablo; Rosa, Ricardo; Ruiz, Daniel
Perspective-based Character Description in Interactive 3D Environments Proceedings Article
In: Congreso Español sobre Tecnologías y Lógica Fuzzy (ESTYLF 2016), San Sebastián, Spain, 2016.
@inproceedings{619,
title = {Perspective-based Character Description in Interactive 3D Environments},
author = {Gonzalo M\'{e}ndez and Raquel Herv\'{a}s and Pablo Gerv\'{a}s and Ricardo Rosa and Daniel Ruiz},
url = {https://www.researchgate.net/publication/298403155_Perspective-based_Character_Description_in_Interactive_3D_Environments},
year = {2016},
date = {2016-05-01},
urldate = {2016-05-01},
booktitle = {Congreso Espa\~{n}ol sobre Tecnolog\'{i}as y L\'{o}gica Fuzzy (ESTYLF 2016)},
address = {San Sebasti\'{a}n, Spain},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hervás, Raquel; Arroyo, Javier; Francisco, Virginia; Peinado, Federico; Gervás, Pablo
Influence of personal choices on lexical variability in referring expressions Journal Article
In: Natural Language Engineering, vol. 22, no. 2, pp. 257-290, 2016, ISSN: 1469-8110.
@article{610,
title = {Influence of personal choices on lexical variability in referring expressions},
author = {Raquel Herv\'{a}s and Javier Arroyo and Virginia Francisco and Federico Peinado and Pablo Gerv\'{a}s},
url = {https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/influence-of-personal-choices-on-lexical-variability-in-referring-expressions/E2207316F17BB91A8276777AE13E4C4D?utm_campaign=shareaholic\&utm_medium=copy_link\&utm_source=bookmark},
doi = {10.1017/S1351324915000182},
issn = {1469-8110},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
journal = {Natural Language Engineering},
volume = {22},
number = {2},
pages = {257-290},
abstract = {Variability is inherent in human language as different people make different choices when facing the same communicative act. In Natural Language Processing, variability is a challenge. It hinders some tasks such as evaluation of generated expressions, while it constitutes an interesting resource to achieve naturalness and to avoid repetitiveness. In this work, we present a methodological approach to study the influence of lexical variability. We apply this approach to TUNA, a corpus of referring expression lexicalizations, in order to study the use of different lexical choices. First, we reannotate the TUNA corpus with new information about lexicalization, and then we analyze this reannotation to study how people lexicalize referring expressions. The results show that people tend to be consistent when generating referring expressions. But at the same time, different people also share certain preferences.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Variability is inherent in human language as different people make different choices when facing the same communicative act. In Natural Language Processing, variability is a challenge. It hinders some tasks such as evaluation of generated expressions, while it constitutes an interesting resource to achieve naturalness and to avoid repetitiveness. In this work, we present a methodological approach to study the influence of lexical variability. We apply this approach to TUNA, a corpus of referring expression lexicalizations, in order to study the use of different lexical choices. First, we reannotate the TUNA corpus with new information about lexicalization, and then we analyze this reannotation to study how people lexicalize referring expressions. The results show that people tend to be consistent when generating referring expressions. But at the same time, different people also share certain preferences.
2015
Hervás, Raquel; Sánchez-Ruiz, Antonio; Gervás, Pablo; León, Carlos
Calibrating a Metric for Similarity of Stories against Human Judgment Proceedings Article
In: Creativity and Experience Workshop, International Conference on Case-Based Reasoning, Bad Homburg, Frankfurt, Germany, 2015.
@inproceedings{609,
title = {Calibrating a Metric for Similarity of Stories against Human Judgment},
author = {Raquel Herv\'{a}s and Antonio S\'{a}nchez-Ruiz and Pablo Gerv\'{a}s and Carlos Le\'{o}n},
year = {2015},
date = {2015-09-01},
urldate = {2015-09-01},
booktitle = {Creativity and Experience Workshop, International Conference on Case-Based Reasoning},
address = {Bad Homburg, Frankfurt, Germany},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gervás, Pablo; Hervás, Raquel; León, Carlos
Generating Plots for a Given Query Using a Case-Base of Narrative Schemas Proceedings Article
In: Creativity and Experience Workshop, International Conference on Case-Based Reasoning, Bad Homburg, Frankfurt, Germany, 2015.
@inproceedings{608,
title = {Generating Plots for a Given Query Using a Case-Base of Narrative Schemas},
author = {Pablo Gerv\'{a}s and Raquel Herv\'{a}s and Carlos Le\'{o}n},
year = {2015},
date = {2015-09-01},
urldate = {2015-09-01},
booktitle = {Creativity and Experience Workshop, International Conference on Case-Based Reasoning},
address = {Bad Homburg, Frankfurt, Germany},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}