The Story Telling Laboratory

The Story Telling Laboratory is a research initiative that brings together ongoing projects that study various areas related to stories: how they are constructed, how they can be explored in an interactive manner, how they are converted into text or video, how their texts are read out aloud in a convincing manner, how they can be rendered as verse...

This page describes the research that has been carried out over the past 20 years. Given the volume of accumulated results, the description has been grouped into sections under headings that seemed descriptive. Some papers may appear under more then one heading, when their content touches upon several topics.

For a description of the motivation behind the general approach of The Story Telling Laboratory and considerations on what topics get addressed when, please read the following entry On Motivation and Expected Impact

Projects that are currently under way within The Story Telling Laboratory are listed below. However, results so far on this line of research have shown that there are many open issues to explore and many different approaches will be required to explore them.

If you think you can contribute to this initiative, please get in touch with us by sending an email message to .

The TSTL acronym pays homage to Robert Louis Stevenson, as a shortened version of Tusitala, which is Samoan for "Teller of Tales", and which he used as a pseudonym.

Narrative

The overall goal of this particular research line is the computational modelling of literary creativity in a broad sense, including both the generation of narrative (this section) and the generation of poetry (see ‘Poetry’ below). Although this has been more a result of changes of funding and personnel over the years (see the ‘Caveat’ above), there is indeed an underlying conviction that adequate modelling of literary endeavours needs to address issues both at the level of content – which is more relevant for narrative – and at the level of form – which is more relevant for poetry. As discussed in the ‘Caveat’ above, the descriptions given below are not intended as a formal theories or exhaustive accounts but rather as reports on partial expeditions of discovery into of small parts of the large territory that we hope to explore in the long run.

For completeness and ease of access, wherever specific papers contain material addressing more than one topic, they are listed below under more than one heading.

General Considerations on Narrative

Although “storytelling” is often used as a monolythic concept, we have found it useful to consider that it might be deconstructed into a number of related concepts that interact to realise its underlying complexity. Our current view of this deconstruction is still in flux, but the following subdivisions have provided us with useful partitions that have allowed significant progress to be made. We are also very much aware that any deconstruction we can consider is only partial, and that many relevant subtasks are still being left out. The following set of subtasks is proposed here only as a means for explaining the work accumulated over the years. In our experience, the different ways in which people use narrative to communicate show a significant presence of the following subtasks:

  • coming up with a narrative structure for the story that it to be told (see ‘Content Determination: Plot building’ below)
  • identifying the best way – in terms of discourse -- of conveying a story that is already fixed – as a fabula (see ‘Discourse Planning: Narrative Composition’ below)
  • assigning value to a representation of narrative at some level of abstraction (see ‘Automated Assessment of Narrative’ below)

This partial deconstruction is very useful to make progress at each of these subtasks, but it also provides the means for “reconstructing” the overall tasks as a combination of the subtasks. A significant part of our research effort has gone into exploring how this might be achieved, constituting therefore an additional partition:

  • how the subtasks above may combine into an integrated model of the storytelling task (see ‘Narrative as an Integrated Process of Specific Subtasks’ below)

Additionally, it became clear that the impact that a narrative has on an audience is heavily influenced by a number of factors that are not necessarily explicit in the surface form of the narrative as the audience receives it, but which are inferred by the audience during interpretation. Examples of this are emotions – both manifested by the characters and experienced by the audience --, affinities between characters, personalities of characters, suspense… Explicit investigation of how these factors may be handled – identified, represented, built – computationally became therefore an additional partition of our research plan:

  • how particular factors not necessarily explicit in the surface form of a narrative are nevertheless relevant to its assessment, and how such factors might be represented computationally (see ‘Elements Relevant to Narrative’ below)

At various points in our trajectory we have made efforts to sit back, review the accumulated work, and reflect upon the insights arising from it. The following two papers constitute two different such efforts, thirteen years apart.

  • P. Gervás, Concepción, E., León, C., Méndez, G., and Delatorre, P., “The Long Path to Narrative Generation”, IBM Journal of Research & Development, vol. 63, pp. 1-8, 2019.
  • P. Gervás, Lönneker, B., Meister, J. C., and Peinado, F., “Narrative Models: Narratology Meets Artificial Intelligence”, in International Conference on Language Resources and Evaluation. Satellite Workshop: Toward Computational Models of Literary Analysis, Genova, Italy, 2006, pp. 44-51.

Representation of Narrative

A fundamental challenge for the development of any artificial intelligence solution is the choice of the right representation of the problem being considered. Ideal as it would have been to find a single representation suitable for all the various tasks related to narrative that we have considered, our experience is that specific tasks are best served by particular representations, and that the resulting set of representations is not necessarily interchangeable or even compatible. The following sections describe some of the insights arising from the specific choices that we have considered. These include representation formats, methodological approaches, or relevant phenomena that have required specific solutions.

Desiderata

When relevant insights have arisen from the accumulation of evidence from working on the same concepts but applied to different tasks and using different technologies, we have made a point of trying to make them available to the scientific community in general in the form of scientific papers. The following two papers constitute instances of this type of effort.

  • E. Concepción, Gervás, P., and Méndez, G., “A common model for representing stories in automatic storytelling”, in 6th International Workshop on Computational Creativity, Concept Invention, and General Intelligence. C3GI 2017, Madrid, Spain, 2017.
  • P. Gervás and León, C., “The Need for Multi-Aspectual Representation of Narratives in Modelling their Creative Process”, in 2014 Workshop on Computational Models of Narrative, Quebec City, Canada, 2014.

Corpora

Corpus-based approaches to computational linguistics have over time have shown great advantages, so they were clearly a valuable tool to consider in our various attempts at solving specific tasks related to narrative. The compilation and annotation of corpora have been important elements in our work to this point on several of these tasks, such as: identification of narrative schemas (see ‘Narrative schemas” below) and emotional connotations of text (see ‘Emotions’ below).

  • P. Gervás, Hervás, R., León, C., and Gale, C. V., “Annotating Musical Theatre Plots on Narrative Structure and Emotional Content”, in Seventh International Workshop on Computational Models of Narrative, Kravov, Poland, 2016.
  • V. Francisco, Hervás, R., Peinado, F., and Gervás, P., “EmoTales: creating a corpus of folk tales with emotional annotations”, Language Resources and Evaluation, vol. 45, 2011.
  • P. Lendvai, Declerck, T., Darányi, S., Gervás, P., Hervás, R., Malec, S., and Peinado, F., “Integration of Linguistic Markup into Semantic Models of Folk Narratives: The Fairy Tale Use Case”, in Seventh conference on International Language Resources and Evaluation (LREC'10), La Valetta, Malta, 2010.
  • P. Gervás, “Corpus Annotation for Narrative Generation Research: A Wish List”, in First International AMICUS Workshop on Automated Motif Discovery in Cultural Heritage and Scientific Communication Texts Satellite event of the Supporting the Digital Humanities Conference (SDH-2010), Vienna, Austria, 2010.

Controlled Natural Language (CNL)

As the number of tasks related to narrative that we considered increased (and the number of technologies, each with their associated representation format) we realised that an important challenge for the field of computational narrative would be to find a reasonable format for interchanging resources / data across different implementations. One of the possibilities we explored as a posible solution to this challenge was the use of Controlled Natural Language, a simple text that is formal enough to be parsed without problema and easily produced from any more complex representation. Such a representation would be easy enough for any computational narrative application to produce. The onus of transcribing outputs from other systems onto the internal notation of each research effort would lie on the implementation of the parser from the Controlled Natural Language onto the internal notation in each case. We relied on this idea to propose a posible format for a shared evaluation task on narrative generation, relying on such a Controlled Natural Language to provide the shared ground data, and on the parsers to evaluate the outputs.

  • E. Concepción, Gervás, P., Méndez, G., and León, C., “A Challenge Proposal for Narrative Generation using CNLs”, in GenChal Special Session at 9th International Natural Language Generation conference, INLG 2016 5-8 September 2016, Edinburgh, Scotland, UK, 2016.
  • E. Concepción, Gervás, P., Méndez, G., and León, C., “Using CNL for Knowledge Elicitation and Exchange across Story Generation Systems”, in 5th Workshop on Controlled Natural Language (CNL 2016), Aberdeen, Scotland, 2016.
  • E. Concepción, Gervás, P., and Méndez, G., “Mining Knowledge in Storytelling Systems for Narrative Generation”, in CC-NLG: Computational Creativity in Natural Language Generation (@INLG2016), Edimburgh, UK, 2016.

Narrative Schemas

As we explored more and more theoretical accounts and computational implementations of various narrative tasks, it soon became clear that an important and useful concept was the idea that there are certain schemas of how information is organised in a narrative that recurr across existing stories in various formats – novels, movies, plays, TV series, folk tales… -- regardless of the mode of presentation and the theory of narrative that is being considered. This concept had so far been explored mostly in accounts closer to the field of creative writing than formal narratology. We decided to explore how such accounts might be useful in computational terms, to generate knowledge resources in a first instance, and to inform generation process once those become available. This particular initiative has also been supported by the work on corpus annotation (see ‘Corpora’ above).

  • P. Gervás, León, C., and Méndez, G., “Schemas for Narrative Generation Mined from Existing Descriptions of Plot”, in Computational Models of Narrative, Atlanta, Georgia, USA, 2015.
  • C. León, “A Computational Model for Automated Extraction of Structural Schemas from Simple Narrative Plots”, Universidad Complutense de Madrid, Madrid, 2010.

Ontologies

Description-logic based ontologies (prevalent in semantic web) are a useful technology for representing complex knowledge, and we have considered them as a posible solution for representing narrative. Most the work described here was the result of Federico Peinado’s PhD thesis, in which he explored a framework for developing applications of automated narration. The ontology he developed included features from Vladimir Propp’s “Morphology of the Folktale” – for the more traditional views on plot and narrative roles of characters -- and from Robert McKee’s work on screenwriting – for more recent views on the progression of stories and interactivity.

  • F. Peinado and Gervás, P., “Un Armazón para el Desarrollo de Aplicaciones de Narración Automática basado en Componentes Ontológicos Reutilizables”, Universidad Complutense de Madrid, Madrid, 2008.
  • F. Peinado and Gervás, P., “Minstrel Reloaded: From the Magic of Lisp to the Formal Semantics of OWL”, in 3rd International Conference on Technologies for Interactive Digital Storytelling and Entertainment (TIDSE), Darmstadt, Germany, 2006, vol. 4326, pp. 93-97.
  • F. Peinado and Gervás, P., “A Generative and Case-based Implementation of Proppian Morphology”, in The 17th Joint International Conference of the Association for Computers and the Humanities and the Association for Literary and Linguistic Computing (ACH/ALLC), Victoria, Canada, 2005, pp. 129-131.
  • F. Peinado, Gervás, P., Díaz-Agudo, B., Veale, T., Cardoso, A., and Camara Pereira, F., “A Description Logic Ontology for Fairy Tale Generation”, in 4th International Conference on Language Resources and Evaluation, Procs. of the Workshop on Language Resources for Linguistic Creativity, Lisbon, Portugal, 2004, pp. 56-61.

Embedded Stories

Over the time we have spent attempting to model narrative, the phenomenon of embedded stories – and the associated concept of narrative levels – has emerged as a very significant feature present in most human narratives yet very rarely considered in computational accounts of narrative. For this reason, some of our most recent work attempts to shed some light on how these features might be addressed computationally.

  • P. Gervás, “A Model of Interpretation of Embedded Stories”, in Text2Story: 4th International Workshop on Narrative Extraction from Texts, Lucca, Tuscany, 2021.

Content Determination: Plot Building

An important task within a computational storytelling set up is the ability to construct new stories. This subtask of the whole alligns well with the stage of content determination in a classical natural language pipeline, where the content to be conveyed is either selected or constructed. The task of deciding how that content should be conveyed constitutes a separate task of discourse planning (see ‘Discourse Planning: Narrative Composition’ below). In terms of classical narratological concepts, this content determination subtask alligns reasonably well with the establishment of the fabula for the story, as opposed to the construction of a specific discourse for a given fabula (see ‘Discourse Planning: Narrative Composition’ below).

This content determination task is what is usually referred to as story generation. Historically, it was the main drive of our initial efforts in this field. During those, it became apparent very early on that a fundamental characteristic which played a very significant role in the perception of quality of a story was whether the events in it were somehow linked by a causal sequence from the start of the story towards its resolution. We therefore adopted the concept of plot defended by Forster – a chronological sequence of events linked by causality – as a driving force in our efforts. That is one of the reasons why most of the papers cited below refer to construction of plot. Another important reason is that we very early on adopted the decision to focus on the construction of conceptual descriptions of the structure of the narrative, leaving for a later stage the generation of either specific linear discourses that narrate it (see ‘Discourse Planning: Narrative Composition’ below) or text renditions of such discourses (these we have not worked much on, though some work is describe in ‘Text Generation’ below).

Our efforts to explore different alternative technologies for addressing the task of constructing plots have ranged over a number of different options:

  • some general solutions difficult to classify are listed below under 'General Efforts on Plot Generation'
  • solutions based on Vladimir Propp’s “Morphology of the FolkTale” (see ‘Propp-Based Approaches to Plot Construction’ below)
  • solutions based on rule-based simulation (see ‘Simulation-Based Approaches to Plot Construction’ below)
  • solutions based on reusing (material from) existing stories (see ‘Case-BasedReasoning Approaches to Plot Construction’ below)
  • solutions based on planners (see ‘Planner-Based Approaches to Plot Construction’ below)

General Efforts on Plot Generation

  • P. Gervás, “Generating a Search Space of Acceptable Narrative Plots”, in 10th International Conference on Computational Creativity (ICCC 2019), UNC Charlotte, North Carolina, USA, 2019.
  • P. Gervás, “Comparative Evaluation of Elementary Plot Generation Procedures”, in 6th International Workshop on Computational Creativity, Concept Invention, and General Intelligence, Madrid, Spain, 2017.
  • G. Méndez, Hervás, R., Gervás, P., Martín, A., and Julca, F., “Exploring Creative Freedom in Real Time Story Generation”, in 4th AISB Symposium on Computational Creativity (AISBCC 2017), University of Bath, UK, 2017.
  • S. Colton, Llano, M. Teresa, Hepworth, R., Charnley, J., Gale, C. V., Baron, A., Pachet, F., Roy, P., Gervás, P., Collins, N., Sturm, B., Weyde, T., Wolff, D., and Lloyd, J. Robert, “The Beyond the Fence Musical and Computer Says Show Documentary”, in Seventh International Conference on Computational Creativity (ICCC 2016), Paris, France, 2016.

Propp-Based Approaches to Plot Construction

  • P. Gervás, “Computational Drafting of Plot Structures for Russian Folk Tales”, Cognitive Computation, 2015.
  • P. Gervás, “Reviewing Propp's Story Generation Procedure in the Light of Computational Creativity”, in AISB Symposium on Computational Creativity, AISB-2014, April 1-4 2014, Goldsmiths, London, UK, 2014.
  • P. Gervás, “Propp’s Morphology of the Folk Tale as a Grammar for Generation”, in Workshop on Computational Models of Narrative, a satellite workshop of CogSci 2013: The 35th meeting of the Cognitive Science Society, Universität Hamburg Hamburg, Germany, 2013.

Simulation-Based Approaches to Plot Construction

  • C. León and Gervás, P., “Creativity in Story Generation From the Ground Up: Non-deterministic Simulation driven by Narrative”, in 5th International Conference on Computational Creativity, ICCC 2014, Ljubljana, Slovenia, 2014.
  • S. Hassan, León, C., Gervás, P., and Hervás, R., “A Computer Model that Generates Biography-Like Narratives”, in International Joint Workshop on Computational Creativity, London, 2007.
  • C. León and Gervás, P., “Prototyping the Use of Plot Curves to Guide Story Generation”, in Workshop on Computational Models of Narrative, 2012 Language Resources and Evaluation Conference (LREC'2012), Istambul, Turkey, 2012.
  • C. León and Gervás, P., “The Role of Evaluation Driven Rejection in the Successful Exploration of a Conceptual Space of Stories”, Minds and Machines, 2010.
  • P. Gervás and León, C., “Story Generation Driven by System-Modified Evaluation Validated by Human Judges”, in First International Conference on Computational Creativity, Lisboa, Portugal, 2010.
  • C. León and Gervás, P., “Creative Storytelling Based on Transformation of Generation Rules”, in 5th Internation Joint Workshop on Computational Creativity, 2008.

Case-Based Reasoning Approaches to Plot Construction

  • P. Gervás, Hervás, R., and León, C., “Generating Plots for a Given Query Using a Case-Base of Narrative Schemas”, in Creativity and Experience Workshop, International Conference on Case-Based Reasoning, Bad Homburg, Frankfurt, Germany, 2015.
  • M. Riedl and León, C., “Toward Vignette-Based Story Generation for Drama Management Systems”, in Workshop on Integrating Technologies for Interactive Stories - 2nd International Conference on INtelligent TEchnologies for interactive enterTAINment , 2008.
  • B. Díaz-Agudo, Gervás, P., and Peinado, F., “A Case Based Reasoning Approach to Story Plot Generation”, in Proceedings of the 7th European Conference on Case Based Reasoning (ECCBR). Advances in Case-Based Reasoning, Madrid, Spain, 2004, pp. 142-156.
  • P. Gervás, Díaz-Agudo, B., Peinado, F., and Hervás, R., “Story Plot Generation based on CBR”, in 24th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence (AI-2004), Cambridge, UK, 2004.

Planner-Based Approaches to Plot Construction

  • I. M. Laclaustra, Ledesma, J. L., Méndez, G., and Gervás, P., “Kill the Dragon and Rescue the Princess: Designing a Plan-Based Multi-agent Story Generator”, in 5th International Conference on Computational Creativity, ICCC 2014 (Late Breaking paper), Ljubljana, Slovenia, 2014.

Discourse Planning: Narrative Composition

Once we had identified that the challenge of automated storytelling benefited significantly from being deconstructed into a number of subtasks (see ‘General Considerations on Narrative’ above), we realised very soon that, while the stage of building a new story -- story generation – was the focus of significant research efforts across the world, the stage of constructing a narrative discourse for an already established story was generally being neglected. This lead to a particular focus within our research group on this subtask over the years.

A number of specific research lines have been considered within this subtask:

  • how to compose a narrative discourse to convey a given set of facts already established (see ‘Composing Narrative Discourse from Facts’ below)
  • how to check computationally if the story you want to convey is the primary interpretation of the discourse you have built (see ‘Composing Narrative Discourse from Facts with Interpretability Check’ below)
  • how to compose a narrative discourse to convey a given set of facts but also considering how such a discourse might best match a particular plot; this would allow different ways of telling about someone’s years at university, allowing for instance the choice of telling it as a tale of achievement – how their hard work led to them getting their current successful job – or as a love story – how they met their current spouse – (see ‘Composing Discourse from Facts to Match a Plot’ below)
  • how a number of subplots can be combined together into a single discourse sequence (see ‘Building Stories with Subplots’ below)

Composing Narrative Discourse from Facts

  • P. Gervás, “Empirical Determination of Basic Heuristics for Narrative Content Planning”, in Proceedings of Computational Creativity and Natural Language Generation Workshop, International Conference on Natural Language Generation (INLG 2016), Edimburgh, Scotland, 2016.
  • P. Gervás, “Narrative Discourse as a Target Format for Data to Text Generation”, in 1st International Workshop on Data-to-Text Generation, Edimburgh, 2015.
  • P. Gervás, “Composing Narrative Discourse for Stories of Many Characters: a Case Study over a Chess Game”, Literary and Linguistic Computing, vol. 29, 2014.
  • P. Gervás, “Metrics for Desired Structural Features for Narrative Renderings of Game Logs”, Journal of Entertainment Computing, 2014.
  • P. Gervás, “Narrative Composition: Achieving the Perceived Linearity of Narrative”, in Proceedings of the 14th European Workshop on Natural Language Generation, Sofia, Bulgaria, 2013.
  • P. Gervás, “Stories from Games: Content and Focalization Selection in Narrative Composition”, in I Spanish Symposium on Entertainment Computing, Universidad Complutense de Madrid, Madrid, Spain, 2013.
  • P. Gervás, “From the Fleece of Fact to Narrative Yarns: a Computational Model of Composition”, in Workshop on Computational Models of Narrative, 2012 Language Resources and Evaluation Conference (LREC'2012) , Istambul, Turkey, 2012.
  • C. León, Hassan, S., Gervás, P., Olivier, P., and Kray, C., “From the Event Log of a Social Simulation to Narrative Discourse: Content Planning in Story Generation”, in Conference of the Artificial and Ambient Intelligence, Culture Lab, Newcastle University, Newcastle upon Tyne, UK, 2007, pp. 402–409.

Composing Narrative Discourse from Facts with Interpretability Check

  • P. Gervás, “An Exploratory Model of Remembering, Telling and Understanding Experience in Simple Agents”, in Proceedings of Computational Creativity, Concept Invention, and General Intelligence Workshop (C3GI 2016), Bolzano, Italy, 2016.
  • P. Gervás, “Composing Narrative Discourse for Stories of Many Characters: a Case Study over a Chess Game”, Literary and Linguistic Computing, vol. 29, 2014.

Composing Discourse from Facts to Match a Plot

  • P. Gervás, “Storifying Observed Events: Could I Dress This Up as a Story?”, in 5th AISB Symposium on Computational Creativity, University of Liverpool, UK, 2018.
  • P. Gervás, “Targeted Storyfying: Creating Stories About Particular Events”, in Ninth International Conference on Computational Creativity, ICCC 2018, Salamanca, Spain, 2018.

Building Stories with Subplots

  • E. Concepción, Gervás, P., and Méndez, G., “Exploring Baselines for Combining Full Plots into Multiple-plot Stories”, New Generation Computing, pp. 1-41, 2020.
  • E. Concepción, Gervás, P., and Méndez, G., “Evolving the INES story generation system: from single to multiple plot lines”, in 10th International Conference on Computational Creativity (ICCC 2019), UNC Charlotte, North Carolina, USA, 2019.
  • P. Gervás, “Generating a Search Space of Acceptable Narrative Plots”, in 10th International Conference on Computational Creativity (ICCC 2019), UNC Charlotte, North Carolina, USA, 2019.

Elements Relevant to Narrative

The impact of a given narrative on its audience is significantly affected by a number of factors that are not necessarily explicit in the surface form of the narrative as the audience receives it, but which all audiences identify without difficulty during interpretation and use to construct their opinion of it. There are many factors that fall within this category. At the present time, only a few of them have been the focus of explicit exploration within our research group. The extent of our research in each case is described below:

  • the emotions experienced by either the characters in the story or the members of the audience on reacting to the story (see ‘Emotions’ below)
  • the interplay of affinities between characters as it evolves through the story (see ‘Character Affinity’ below)
  • the personality of the characters as described in the story or perceived by the audience (see ‘Character Personality’ below)
  • the level of suspense induced in the audience by the story, either deliberately sought by the construction process or not (see ‘Modelling Suspense’ below)

Emotions

Emotions are clearly central to narrative. Indeed, one of the main purposes of narrative seems to be to allow an author to induce or convey a given set of emotions to an audience, to such an extent that these emotions are themselves very difficult to represent or describe separately from the narrative form. Given their importance we have considered over the years several approaches at identifying or representing emotions computationally. These efforts attempt to take into account existing psychological theories of emotion, and tend to focus on the relation between particular emotions and words that may be used in conveying them to others. In support of this initiative we have developed corpora, ontologies and lexical resources. We have explored emotional labels, a space of emotional coordinates, and polarity/intensity values. We have developed automated taggers and automated classifiers. We are still trying to find a way of exploiting the knowledge acquired in this task to other tasks.

Annotation of Emotions

  • P. Gervás, Hervás, R., León, C., and Gale, C. V., “Annotating Musical Theatre Plots on Narrative Structure and Emotional Content”, in Seventh International Workshop on Computational Models of Narrative, Kravov, Poland, 2016.
  • V. Francisco, Peinado, F., Hervás, R., and Gervás, P., “Semantic Web Approaches to the Extraction and Representation of Emotions in Texts ”, in Semantic Web: Standards, Tools and Ontologies, NOVA Publishers, 2010.
  • V. Francisco and Hervás, R., “EmoTag: Automated Mark Up of Affective Information in Texts”, in EUROLAN 2007 Summer School Doctoral Consortium, Iasi, Romania, 2007, pp. 5–12.
  • V. Francisco, Hervás, R., and Gervás, P., “Two Different Approaches to Automated Mark Up of Emotions in Text”, in AI-2006, Cambridge, England, 2006, pp. 101–114.
  • V. Francisco, Gervás, P., and Hervás, R., “Análisis y síntesis de expresión emocional en cuentos leídos en voz alta”, Sociedad Española para el Procesamiento del Lenguaje Natural, vol. 35, pp. 293–300, 2005.
  • V. Francisco, Gervás, P., and Hervás, R., “Expresión de emociones en la síntesis de voz en contextos narrativos”, in Primer Simposio sobre Computación Ubicua e Inteligencia Ambiental (UCAmi'05), Granada, Spain, 2005, pp. 353–360.
  • V. Francisco and Gervás, P., “EmoTag: An Approach to Automated Markup of Emotions in Texts”, Computational Intelligence, 2012.
  • V. Francisco, Hervás, R., Peinado, F., and Gervás, P., “EmoTales: creating a corpus of folk tales with emotional annotations”, Language Resources and Evaluation, vol. 45, 2011.
  • V. Francisco, Gervás, P., and Peinado, F., “Ontological reasoning for improving the treatment of emotions in text”, Knowledge and Information Systems, vol. 24, p. 23, 2010.
  • V. Francisco, Peinado, F., Hervás, R., and Gervás, P., “Semantic Web Approaches to the Extraction and Representation of Emotions in Texts ”, in Semantic Web: Standards, Tools and Ontologies, NOVA Publishers, 2010.
  • V. Francisco and Gervás, P., “Ontology-Supported Automated Mark Up of Affective Information in Texts”, Special Issue of Language Forum on Computational Treatment of Language, vol. 34, pp. 23 - 36, 2008.

Sentiment Analysis (polarity/intensity)

  • J. Carrillo de Albornoz and Plaza, L., “An Emotion-based Model of Negation, Intensifiers, and Modality for Polarity and Intensity Classification”, Journal of the American Society for Information Science and Technology (JASIST). In press, 2012.
  • J. Carrillo de Albornoz, Plaza, L., and Gervás, P., “SentiSense: An easily scalable concept-based affective lexicon for Sentiment Analysis”, in The 8th International Conference on Language Resources and Evaluation (LREC 2012), 2012.
  • J. Carrillo de Albornoz, “Combining Linguistic and Semantic Information in an Emotion-based Model for Polarity and Intensity Classification”, 2011.

Character Affinity

The evolution over time of relations between characters is another very important element in narrative. Again, narrative seems indeed to be the prefered means in our culture to convey this type of information. We have explored various possible ways of representing character affinity and taking it into account when building stories: Bayesian models, fuzzy logic, agent-based systems, BDI models.

  • P. Kalluri and Gervás, P., “Affinity-based Interpretation of Triangle Social Scenarios”, in Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,, 2017.
  • G. Méndez, Gervás, P., and León, C., “On the Use of Character Affinities for Story Plot Generation”, in Knowledge, Information and Creativity Support Systems: Selected Papers from KICSS’2014, vol. 416, Springer, 2016, pp. 211-225.
  • G. Méndez, Gervás, P., and León, C., “Using Fuzzy Logic to Model Character Affinities for Story Plot Generation”, in Congreso Español sobre Tecnologías y Lógica Fuzzy (ESTYLF 2016), San Sebastián, Spain, 2016.
  • G. Méndez, Gervás, P., and León, C., “A Model of Character Affinity for Agent-Based Story Generation”, in 9th International Conference on Knowledge, Information and Creativity Support Systems, Limassol, Cyprus, 2014.
  • F. Peinado, Cavazza, M., and Pizzi, D., “Revisiting Character-Based Affective Storytelling under a Narrative BDI Framework”, in International Conference on Interactive Digital Storytelling, Erfurt, Germany, 2008.

Character personality

The personality of characters is also a fundamental ingredient of narrative. Stories that have characters with rich personalities draw the attention of the audience, and coherence between the personality of characters and their actions seems to play a fundamental role in the perception of the quality of a story.

  • F. Julca, Méndez, G., and Hervás, R., “An Internal Model for Characters in Virtual Environments”, in Virtual Reality Designs, 1stst ed., Boca Raton: CRC Press, 2020.
  • M. Wilder and Gervás, P., “A Model of Character Evolution based on Stanislavsky-driven BDI Agents”, in 6th International Workshop on Computational Creativity, Concept Invention, and General Intelligence, Madrid, Spain, 2017.
  • H. Gómez-Gauchía and Peinado, F., “Automatic Customization of Non-Player Characters Using Players Temperament”, in 3rd International Conference on Technologies for Interactive Digital Storytelling and Entertainment (TIDSE), Darmstadt, Germany, 2006, vol. 4326, pp. 241-252.

Modelling Suspense

Suspense is a complex abstract concept very often used when discussing the quality of narrative media (movies, games, stories…) or their impact on the audience. We have looked into psychological theories of suspense and carried out empirical work on trying to identify how the various possible mechanisms of suspense operate on audience perceptions of narrative.

  • P. Delatorre, Salguero, A., León, C., and Tapscott, A., “The Impact of Context on Affective Norms: A Case of Study With Suspense”, Frontiers in Psychology, vol. 10, p. 1988, 2019.
  • P. Delatorre, León, C., Salguero, A., Palomo-Duarte, M., and Gervás, P., “Information management in interactive and non-interactive suspenseful storytelling”, Connection Science, vol. 31, pp. 82-101, 2019.
  • P. Delatorre, León, C., Salguero, A. G., Palomo-Duarte, M., and Gervás, P., “Confronting a paradox: a new perspective of the impact of uncertainty in suspense”, Frontiers in Psychology, vol. 9, p. 1392, 2018.
  • P. Delatorre, León, C., Salguero, A., Palomo-Duarte, M., and Gervás, P., “Outcome inference based on threat resources in suspenseful scenes”, in Proceedings of 5th AISB Symposium on Computational Creativity 2018, Liverpool (UK), 2018.
  • P. Delatorre, León, C., Gervás, P., and Palomo-Duarte, M., “A computational model of the cognitive impact of decorative elements on the perception of suspense”, Connection Science, vol. 29, pp. 295-331, 2017.
  • P. Delatorre, León, C., Salguero, A., Mateo-Gil, C., and Gervás, P., “Impact of interactivity on information management for suspense in storytelling”, in Proceedings of AISB Annual Convencion 2017, 2017.
  • P. Delatorre, León, C., Palomo-Duarte, M., and Gervás, P., “Adding Suspense to a Story Generation System through a Cognitive Model of the Impact of affective Terms”, in: Proceedings of the Sixth International Workshop on Computational Creativity, Concept Invention, and General Intelligence (C3GI 2017), Madrid, Spain.
  • P. Delatorre, Arfè, B., Gervás, P., and Palomo-Duarte, M., “A component-based architecture for suspense modelling”, in Proceedings of AISB 2016's Third International Symposium on Computational Creativity (CC2016), 2016.
  • P. Delatorre, Palomo-Duarte, M., and Gervás, P., “Formalising suspense from immersive environments”, in Proceedings 3rd Congreso de la Sociedad Española para las Ciencias del Videojuego, 2016.
  • P. Delatorre, “Tres perspectivas del suspense formal”, in I Congreso de Jóvenes Investigadores de la Comunicación, 2016.
  • P. Delatorre, Berns, A., Palomo-Duarte, M., Gervás, P., and Madueño, F., “Diseño de un Juego Serio basado en el Suspense”, in Proceedings 2nd Congreso de la Sociedad Española para las Ciencias del Videojuego, Barcelona, Spain, June 24, 2015, 2015.
  • P. Delatorre, Gervás, P., and Palomo-Duarte, M., “Estudios preliminares sobre el suspense narrativo e interactivo”, in VI Jornadas Predoctorales de la Escuela Superior de Ingeniería, 2015.
  • P. Delatorre and Arfè, B., “Modulare la suspense del lettore attraverso un modelo computazionale”, in XXVIII Congresso Nazionale Sezione di Psicologia dello sviluppo e dell'educazione, 2015.

Computational Asssessment of Narrative

In general terms the ability to assess the quality of system outputs is known to be critical for many artificial intelligence approaches – Generate and Test, fitness functions in evolutionary solutions… In recent times the Computational Creativity community developed a strict preference for systems that included the ability to rate their own outputs. Cognitive models of the writing task assign significant important to a cyclic approach that includes reflection-based revisión of intermediate drafts. All these considerations show the importance of having adequate models of how narrative may be assessed computationally.

As in other cases considered above, there are many factors that ought to be considered in the assessment of narrative, and our research group has only manged to consider some of them to this point. The list of factors considered is no way exhaustive – there are many others that should be considered with at least equal or even higher priority – and the efforts described here are in all cases only initial approximations to the task. For what they are worth, the following factors have been explored:

  • what is included in a story (see ‘Content’ below)
  • to what extent a story satisfies expected structural features (see ‘Structure’ below)
  • to what extent a story differs from know stories (see ‘Novelty’ below)

Content

  • P. Gervás, “Comparative Evaluation of Elementary Plot Generation Procedures”, in 6th International Workshop on Computational Creativity, Concept Invention, and General Intelligence, Madrid, Spain, 2017.
  • A. Tapscott, Gómez, J., León, C., Smailovic, J., Znidarsic, M., and Gervás, P., “Empirical Evidence of the Limits of Automatic Assessment of Fictional Ideation”, in C3GI at ESSLLI 2016 Computational Creativity, Concept Invention, and General Intelligence, 2016.
  • F. Peinado and Gervás, P., “Evaluation of Automatic Generation of Basic Stories”, New Generation Computing, vol. 24, pp. 289-302, 2006.

Structure

  • P. Gervás, “Metrics for Desired Structural Features for Narrative Renderings of Game Logs”, Journal of Entertainment Computing, 2014.

Novelty

  • R. Hervás, Sánchez-Ruiz, A., Gervás, P., and León, C., “Calibrating a Metric for Similarity of Stories against Human Judgment”, in Creativity and Experience Workshop, International Conference on Case-Based Reasoning, Bad Homburg, Frankfurt, Germany, 2015.
  • F. Peinado, Francisco, V., Hervás, R., and Gervás, P., “Assessing the Novelty of Computer-Generated Narratives using Empirical Metrics”, MINDS AND MACHINES, vol. 20, p. 588, 2010.

Narrative as an Integrated Process of Specific Subtasks

In trying to model the construction of narrative computationally we aim neither to mirror necessarily the observed characteristics of how humans do it, nor to restrict ourselves to the processes featured in the latest fashion in artificial intelligence technologies. Instead we hope to find a happy medium that combines the best from both worlds. To this end we have come up with a deconstruction of the storytelling process into a number of subtasks that make sense in terms of how humans adresss narrative and that at the same time are suitable for computational modelling. This approach has lead to work on how these subtasks might be fruitfully combined into complex models of the storytelling task in a broader sense.
Our efforts on this research lines have addressed the following topics:

  • computational models of how human cognitive abilities are involved in handling narrative (see ‘Cognitive Issues related to Narrative’ below)
  • computational models of how the tasks of narrative construction, narrative composition and narrative assessment might be integrated into cyclic process of incremental improvement of intermediate drafts (see ‘Interpretation and Revision’ below)
  • specific attempts to build integrated models of the narrative construction task in terms of existing technologies for software architectures (see ‘StoryTelling Architectures’ below)
  • models of how some of these subtasks might be used in colaborative applications that involve a human participant, whether for co-creation of narratives or solutions for existing genres like interactive fiction or videogames (see ‘Colaborative Narrative Creation’ below)

Cognitive Issues related to Narrative

  • C. León, Gervás, P., and Delatorre, P., “Empirical Insights Into Short Story Draft Construction”, IEEE Access, vol. 7, pp. 119192-119208, 2019.
  • C. León, “An architecture of narrative memory”, Biologically Inspired Cognitive Architectures, vol. 16, 2016.

Interpretation and Revision

  • P. Gervás and León, C., “Integrating Purpose and Revision into a Computational Model of Literary Generation”, in Creativity and Universality in Language, Esposti, Mirko Degli, Altmann, Eduardo, Pachet, Francois (Eds.)., Springer, 2016.
  • P. Gervás and León, C., “Corregir e innovar corrigiendo: modelos de creatividad literaria como ciclo de reflexión-revisión”, in Creatividad Computacional, Pérez y Pérez R. (Ed.)., México D. F: UAM-Cuajimalpa-Patria, 2015.
  • P. Gervás and León, C., “When Reflective Feedback Triggers Goal Revision: a Computational Model for Literary Creativity”, in AI and Feedback, IJCAI 2015, Buenos Aires, 2015.
  • P. Gervás and León, C., “Reading and Writing as a Creative Cycle: The Need for a Computational Model”, in 5th International Conference on Computational Creativity, ICCC 2014, Ljubljana, Slovenia, 2014.

StoryTelling Architecture

  • E. Concepción, Gervás, P., and Méndez, G., “A microservice-based architecture for story generation”, in Microservices, Odense, Denmark, 2017.
  • P. Delatorre, Arfè, B., Gervás, P., and Palomo-Duarte, M., “A component-based architecture for suspense modelling”, in Proceedings of AISB 2016's Third International Symposium on Computational Creativity (CC2016), 2016.
  • P. Gervás, “Deconstructing Computer Poets: Making Selected Processes Available as Services”, Computational Intelligence, 2015.

Colaborative Narrative Creation

Assisted Narrative Creation

  • E. Concepción, Gervás, P., and Méndez, G., “An API-based approach to co-creation in automatic storytelling”, in 6th International Workshop on Computational Creativity, Concept Invention, and General Intelligence. C3GI 2017, Madrid, Spain, 2017.
  • C. León and Gervás, P., “Assisting Writing Through Step-by-Step Story Generation”, in Semi-Automated Creativity Workshop, ACM conference on Creativity & Cognition 2011, Atlanta, Georgia, USA., 2011.
  • C. León and Gervás, P., “A Top-Down Design Methodology based on Causality and Chronology for Developing Assisted Story Generation Systems”, in 8th ACM conference on Creativity and cognition, Atlanta, Georgia, USA., 2011.
  • P. Gervás, Pérez y Pérez, R., Sosa, R., and Lemaitre, C., “On the Fly Collaborative Story-Telling: Revising Contributions to Match a Shared Partial Story Line.”, in International Joint Workshop on Computational Creativity, London, 2007.

Interactive Narrative

  • C. León, Peinado, F., and Navarro, A., “An Intelligent Plot-Centric Interface for Mastering Computer Role-Playing Games”, in First Joint International Conference on Interactive Digital Storytelling, Erfurt, Germany, 2008.
  • F. Peinado, Navarro, A., and Gervás, P., “A Testbed Environment for Interactive Storytellers”, in 2nd International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN), Playa del Carmen, Cancun, Mexico, 2008.
  • F. Peinado and Gervás, P., “Automatic Direction of Automatic Storytelling: Formalizing the Game Master Paradigm”, in 4th International Conference on Virtual Storytelling: Using Virtual Reality Technologies for Storytelling (ICVS), Saint-Malo, France, 2007, vol. 4871, pp. 196-201.
  • F. Peinado and Navarro, A., “RCEI: An API for Remote Control of Narrative Environments”, in 4th International Conference on Virtual Storytelling: Using Virtual Reality Technologies for Storytelling (ICVS), Saint-Malo, France, 2007, vol. 4871, pp. 181-186.
  • F. Peinado, “Interactive Digital Storytelling: Automatic Direction of Virtual Environments”, Upgrade, vol. VII, pp. 42-46, 2006.
  • F. Peinado, “Narración Digital e Interactiva: Dirección automática de entornos virtuales”, Novática, vol. 180, 2006.
  • F. Peinado, Gervás, P., and Moreno-Ger, P., “Interactive Storytelling in Educational Environments”, in 3rd International Conference on Multimedia and ICT´s in Education (m-ICTE): Recent Research Developments in Learning Technologies, Caceres, Spain, 2005, vol. 3, pp. 1345-1349.
  • F. Peinado, Ancochea, M., Gervás, P., and Gupta, K. M., “Automated Control of Interactions in Virtual Spaces: a Useful Task for Exploratory Creativity”, in 7th European Conference on Case Based Reasoning. First Joint Workshop on Computational Creativity, Madrid, Spain, 2004, pp. 191-202.
  • F. Peinado and Gervás, P., “Transferring Game Mastering Laws to Interactive Digital Storytelling”, in International Conference on Technologies for Interactive Digital Storytelling and Entertainment, Darmstadt, Germany, 2004.

Text Generation

The ongoing research effort on automated storytelling is focused mainly on higher level tasks such as story construction and narrative composition, and critical ancillary aspects such as narrative representation, overall system architecture or computational modelling of aspects relevant to narrative (see sections above for details). Nevertheless, some effort has been devoted over the years to specific tasks related to the generation of text, either intended to be integrated in a storytelling system or into a poetry generation system.

Descriptive Text

Existing solutions for story generation tend to focus mostly on compiling the sequence of events that constitutes a story, with the descriptions of places and characters either altogether ommited or delegated to an accompanying graphical interface akin to those used for video games. Research on how to generate descriptive text for the conceptual representation of a given element relevant to a story was an important challenge that we hope to integrate in the future into the overall storytelling solution.

Character Description

  • G. Méndez, Hervás, R., Gervás, P., de la Rosa, R., and Ruiz, D., “Adapting Descriptions of People to the Point of View of a Moving Observer”, in 11th International Conference on Natural Languaje Generation (INLG), Tilburg, The Netherlands, 2018.
  • G. Méndez, Hervás, R., Gervás, P., de la Rosa, R., and Ruiz, D., “Perspective-based Character Description in Interactive 3D Environments”, in Congreso Español sobre Tecnologías y Lógica Fuzzy (ESTYLF 2016), San Sebastián, Spain, 2016.
  • G. Méndez, Hervás, R., Bautista, S., Rabadán, A., and Rodríguez-Ferreira, T., “Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images”, in International Natural Language Generation Conference (INLG2017), Santiago de Compostela, Spain, 2017.

Lexical Choice in Referring Expresions

  • R. Hervás, Francisco, V., and Gervás, P., “Assessing the influence of personal preferences on the choice of vocabulary for natural language generation”, Information Processing and Management, vol. 49, 2013.
  • R. Hervás and Finlayson, M., “The Prevalence of Descriptive Referring Expressions in News and Narrative”, in 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010), Uppsala, Sweden, 2010.
  • C. León, de la Puente, S., Dionne, D., Hervás, R., and Gervás, P., “Constructing World Abstractions for Natural Language in Virtual 3D Environments”, in 2nd International Symposium on Intelligent Interactive Multimedia Systems and Services, Mogliano Veneto, Italy, 2009.
  • R. Hervás and Gervás, P., “Evolutionary and Case-Based Approaches to REG: NIL-UCM-EvoTAP, NIL-UCM-ValuesCBR and NIL-UCM-EvoCBR”, 12th European Workshop on Natural Language Generation (ENLG'09). Athens, Greece, 2009.
  • R. Hervás, “Expresiones de Referencia y Figuras Retóricas para la Distinción y Descripción de Entidades en Discursos Generados Automáticamente (Spanish version)”, UCM, 2009.
  • R. Hervás, “Referring Expressions and Rhetorical Figures for Entity Distinction and Description in Automatically Generated Discourses (extended summary in English)”, UCM, 2009.
  • R. Hervás and Gervás, P., “Degree of Abstraction in Referring Expression Generation and its Relation with the Construction of the Contrast Set”, Fifth International Natural Language Generation Conference (INLG'08). Ohio, USA, pp. 161-164, 2008.
  • R. Hervás and Gervás, P., “Descripción de Entidades y Generación de Expresiones de Referencia en la Generación Automática de Discurso”, Procesamiento de Lenguaje Natural, vol. 41, pp. 217-224, 2008.
  • P. Gervás, Hervás, R., and León, C., “NIL-UCM: Most-Frequent-Value-First Attribute Selection and Best-Scoring-Choice Realization”, in Referring Expression Generation Challenge 2008, Proc. of the 5th International Natural Language Generation Conference (INLG'08), Ohio, USA, 2008.
  • R. Hervás and Gervás, P., “NIL: Attribute Selection for Matching the Task Corpus Using Relative Attribute Groupings Obtained from the Test Data”, in First NLG Challenge on Attribute Selection for Generating Referring Expressions (ASGRE), UCNLG+MT Workshop, Machine Translation Summit XI, Copenhagen, Denmark, 2007.

Evolutionary Solution for Referring Expression Generation

  • R. Hervás and Gervás, P., “Applying Genetic Algorithms to Referring Expression Generation and Aggregation”, in 10th International Conference on Computer Aided Systems Theory (EUROCAST), Spain, 2005, pp. 145-149.
  • R. Hervás and Gervás, P., “An Evolutionary Approach to Referring Expression Generation and Aggregation”, in 10th European Workshop on Natural Language Generation (ENLG'05), Aberdeen, England, 2005, pp. 168-173.

Dialogue in Narrative

Dialogue has a fundamental role to play in narrative, to the extent that it is a very important medium for conveying narrative momentum in very prevalent genres (film and drama). Yet in prevailing approaches to computational storytelling it is generally either overlooked altogether or addressed with very basic template-based solutions that are far behing the state of the art in text generation. The recent emergence of chatbots as a promising field and the current trend of using Transformers for all natural language tasks are slowly changing this, but there is still a lot of work to do in alligning these efforts with the accumulated body of knowledge on narrative. At the risk of disappointing those that believe that these new technologies can solve all without resorting to any prior efforts, we do believe that a significant part of the complexity of narrative will still require knowledge-based solutions.

  • A. Oñate, Méndez, G., and Gervás, P., “Emolift: Elevator Conversations based on Emotions”, in 10th International Conference on Computational Creativity (ICCC 2019), UNC Charlotte, North Carolina, USA, 2019.
  • A. Oñate, Méndez, G., and Gervás, P., “Introducing Mood and Affinity to Generate Brief Template-based Dialogues in Storytelling Systems”, in C3GI: The 7th International Workshop on Computational Creativity, Concept Invention, and General Intelligence, Bozen-Bolzano, Italy, 2019.
  • A. Aggarwal, Gervás, P., and Hervás, R., “Measuring the Influence of Errors Induced by the Presence of Dialogues in Reference Clustering of Narrative Text”, 7th International Conference on Natural Language Processing (ICON 09). Hyderabad, India, pp. 209-218, 2009.
  • C. León, Hassan, S., Gervás, P., and Pavón, J., “Mixed Narrative and Dialog Content Planning Based on BDI Agents”, in XII Conferencia de la Asociación Española para Inteligencia Artificial, Salamanca, Spain, 2007.

Rhetorical Figures

Rhetorical figures such as comparisons, analogies and metaphors are often considered informative indicators of the level of literary aspiration of a text: if a text has metaphors or comparisons, then one can asume that the author is making an effort to impress his audience at an aesthetic level. It would therefore seem useful to a computational program with literary aspirations to have access to such tropes. This simple truth has met with the obstacle of the inherent difficulty of modelling these rhetorical devices, but the lack of success has not been lack of attempts or perseverance. The papers listed below cover various attempts in our research group over the years to model the task of constructing rhetorical figures. The most significant difficulties in this task lie in the fact that these figures operate at the semantic and pragmatic levels of linguistics, which are at present the ones most poorly covered by computational solutions.

  • V. Francisco, Hervás, R., Méndez, G., and Galván, P., “Exploring the Potential of Concept Associations for the Creative Generation of Linguistic Artifacts: a Case Study with Riddles and Rhetorical Figures”, Frontiers in Psychology, vol. 9, 2018.
  • P. Galván, Francisco, V., Hervás, R., Méndez, G., and Gervás, P., “Exploring the Role of Word Associations in the Construction of Rhetorical Figures”, in 7th International Conference on Computational Creativity (ICCC 2016), Paris, France, 2016.
  • P. Galván, Francisco, V., Hervás, R., and Méndez, G., “Riddle Generation using Word Associations”, in Language Resources and Evaluation Conference (LREC 2016), Portoroz, Slovenia, 2016.
  • R. Hervás, “Referring Expressions and Rhetorical Figures for Entity Distinction and Description in Automatically Generated Discourses (extended summary in English)”, UCM, 2009.
  • R. Hervás, Costa, R., Costa, H., Gervás, P., and Camara Pereira, F., “Enrichment of Automatically Generated Texts using Metaphor”, in 6th Mexican International Conference on Artificial Intelligence (MICAI-07), Aguascalientes, Mexico, 2007, vol. 4827, pp. 944–954.
  • R. Hervás, Camara Pereira, F., Gervás, P., and Cardoso, A., “Cross-Domain Analogy in Automated Text Generation”, in 3rd Joint Workshop on Computational Creativity, dentro de la 17th European Conference on Artificial Intelligence, Italy, 2006, pp. 43-48.
  • F. Camara Pereira, Hervás, R., Gervás, P., and Cardoso, A., “A Multiagent Text Generator with Simple Rhetorical Habilities”, in Computational Aesthetics: Artificial Intelligence Approaches to Beauty and Happiness (Workshop from AAAI-06), Boston, USA, 2006, pp. 37-44.
  • R. Hervás, Camara Pereira, F., Gervás, P., and Cardoso, A., “A Text Generation System that Uses Simple Rhetorical Figures”, Procesamiento de Lenguaje Natural, vol. 37, pp. 199-206, 2006.

Poetry

Three fundamental premises must be kept in mind when reading the considerations below on computational modelling of poetry generation.

  1. Poetry generation should ideally be viewed as a refinement on prose generation, involving an additional layer of aesthetic requirements on top of the fundamental requirements on content that any literary product should satisfy.
  2. An approach to this task from an engineering point of view may consider the computational modelling of the aesthetic requirements on their own, leaving aside the requirements on content, to allow for progress to be made without the complication of the joint problem.
  3. Any computational solutions arising from this effort should not be viewed as “poets” but rather as modules that might be useful as constituent elements of an automated poet (if and only when they have been integrated with appropriate solutions for producing adequate content).

The prevalent error of labelling any program that produces poem-like artifacts as a computer poet – in which some of our earlier papers described below did indeed incurr – is conceptually incorrect and leads to extremely misleading expectations. These misleading expectations often cloud the appropriate attribution of merit to such efforts.

The poetry-aware computational models described below might at some point in the future be integrated with some of the modules on generation of narrative discourse described above. If and when that happens, they would have at least a semblance of the most elementary abilities of a human author: some means of deciding what content they should include, in what order they should present it, and some idea of how it might be received by their audience. In their present form they have none of these, so their output should be assessed exclusively in terms of the aspects they consider when building it, which are currently restricted to meter, rhyme, stanza structure and some elementary restrictions on linguistic likelihood of the sequences of words they include.

Poetry Generation

The research efforts described below have been grouped into the following categories for ease of access:

  • papers dealing with automated assessment of poetic outputs (see ‘Evaluation’ below)
  • papers dealing with extension of poetic output generators to more than one language (see ‘Multilingual’ below)
  • papers describing methods for building poetic outputs relying on n-gram based models of language (see ‘N-gram Based’ below)
  • papers describing methods for building poetic outputs by reusing material from existing poems at a slightly higher level of granularity (see ‘Case-Based Reasoning’ below)
  • papers describing methods for building poetic outputs relying on rules (see ‘Rule-based’ below)

Evaluation

  • P. Gervás, “Exploring Quantitative Evaluation of the Creativity of Automatic Poets”, in Computational Creativity - The Philosophy and Engineering of Autonomously Creative Systems, T. Veale and F. Cardoso, A. Springer, 2019, p. 275--304.
  • P. Gervás, “Exploring Quantitative Evaluations of the Creativity of Automatic Poets”, in Workshop on Creative Systems, Approaches to Creativity in Artificial Intelligence and Cognitive Science, 15th European Conference on Artificial Intelligence, 2002.
  • P. Gervás, “WASP: Evaluation of Different Strategies for the Automatic Generation of Spanish verse”, in Symposium on Creative & Cultural Aspects and Applications of AI & Cognitive Science, University of Birmingham, England, 2000.

Multilingual

  • H. G. Oliveira, Hervás, R., Díaz, A., and Gervás, P., “Multilingual extension and evaluation of a poetry generator”, Natural Language Engineering, pp. 1–39, 2017.
  • H. G. Oliveira, Hervás, R., Díaz, A., and Gervás, P., “Adapting a Generic Platform for Poetry Generation to Produce Spanish Poems”, in 5th International Conference on Computational Creativity, ICCC 2014, Ljubljana, Slovenia, 2014.

N-gram based

  • P. Gervás, “Template-Free Construction of Poems with Thematic Cohesion and Enjambment”, in Computational Creativity in Language Generation (CC-NLG 2017) workshop, International Natural Language Generation Conference, Santiago de Compostela, Spain, 2017.
  • P. Gervás, “Constrained Creation of Poetic Forms During Theme-Driven Exploration of a Domain Defined by an N-gram Model”, Connection Science, 2016.
  • P. Gervás, “Deconstructing Computer Poets: Making Selected Processes Available as Services”, Computational Intelligence, 2015.
  • P. Gervás, “Tightening the Constraints on Form and Content for an Existing Computer Poet”, in AISB 2015 Symposium on Computational Creativity, University of Kent, Canterbury, United Kingdom, 2015.
  • P. Gervás, “Computational Modelling of Poetry Generation”, in Artificial Intelligence and Poetry Symposium, AISB Convention 2013, University of Exeter, United Kingdom, 2013.
  • P. Gervás, “Evolutionary Elaboration of Daily News as a Poetic Stanza”, in IX Congreso Español de Metaheurísticas, Algoritmos Evolutivos y Bioinspirados - MAEB 2013, Universidad Complutense de MAdrid, Madrid, Spain, 2013.
  • P. Gervás, “Dynamic Inspiring Sets for Sustained Novelty in Poetry Generation”, in Second International Conference on Computational Creativity, México City, México, 2011.
  • P. Gervás, “Diez poemas emocionales generados por un computador”, in ¿Puede un computador escribir un poema de amor?, D. Cañas and C. González Tardón, 2010.

Case-Based Reasoning

  • B. Díaz-Agudo, Gervás, P., González-Calero, P. A., Craw, S., and Preece, A., “Poetry Generation in COLIBRI”, in Proceedings of the 6th European Conference on Case Based Reasoning, Aberdeen, Scotland, 2002.
  • P. Gervás, “Generating Poetry from a Prose Text: Creativity versus Faithfulness ”, in AISB 2001 Symposium on Artificial Intelligence and Creativity in Arts and Science, 2001.
  • P. Gervás, “Modeling Literary Style for Semi-automatic Generation of Poetry”, in User Modeling 2001, 8th International Conference, Sonthofen, Germany, 2001, pp. 231-233.

Rule-based

  • P. Gervás, “An Expert System for the Composition of Formal Spanish Poetry”, Journal of Knowledge-Based Systems, vol. 14, pp. 181-188, 2001.
  • P. Gervás, “A Logic Programming Application for the Analysis of Spanish Verse”, in First International Conference on Computational Logic, Imperial College, London, UK, 2000.
  • P. Gervás, “Un modelo computacional para la generación automática de poesía formal en Castellano”, Procesamiento de Lenguaje Natural, pp. 19–26, 2000.
  • P. Gervás, “WASP: Evaluation of Different Strategies for the Automatic Generation of Spanish verse”, in Symposium on Creative & Cultural Aspects and Applications of AI & Cognitive Science, University of Birmingham, England, 2000.
  • P. Gervás and Murciano, R., “Modelling the Generation of Customised Poetry in JESS”, in Proceedings of the Third International Conference on Enterprise Information Systems, 2001, pp. 543-552.