NIL group members

The NIL acronym (Natural Interaction based on Language) identifies a group of researchers and practitioners whose interests converge towards the development of interfaces based on language for modern day IT applications for modifying or finding information, issuing commands, or present output results in a way easy to understand.

Various Artificial Intelligence techniques contribute towards this goal. The mainstay of NIL is obviously a strong Natural Language Processing component. However, the complexities of language interactions require the use of additional techniques of Knowledge Representation, Expert Systems, Case-Based Reasoning, Evolutionary Algorithms, User Modeling and Computational Creativity.

NIL arises in 2005 to provide a minimal infrastructure to house colaborative projects between researchers at Universidad Complutense de Madrid. Nevertheless, it is open to contributions from researchers affiliated at other institutions if they are interested in the stated goals. At the same point, NIL is born with the overall goal of developing the technologies that it researchs on to the point where they can be used for practical applications. For this reason, we are always on the look out for opportunities to test the applicability of our work in real life situations.

  • If you feel your own research might contribute to these goals and you would like to participate in NIL, please contact us.
  • If you think that your business might benefit from applying one of the techniques that we are working on, or you reckon you may have a possible application for one of them, please contact us.



Proyecto WHIM - 1 plaza de investigador postdoctoral

El proyecto europeo WHIM ("The What-If Machine") investiga el siguiente modelo para la generación creativa de ideas: (a) recopilar y analizar información sobre un dominio, para formar una vision somera del mundo de ese dominio, (b) construir un conjunto de ideas del tipo “qué pasaría si” a partir de ese análisis, utilizando nociones de sorpresa, tensión semántica e incongruencia, (c) valorar, ordenar, y seleccionar ideas a partir de la calidad y la cantidad de narraciones que se puedan generar utilizando cada idea, y (d) utilizar la visión del mundo construida, la idea, y las narraciones re

Pablo Gervás at TEDxBARCELONA SCIENCE 2012

Creatome: How to build machines that write tales

Words can create magic. Could we build machines that write tales and predict the feelings poems create? Pablo Gervas is trying to discover if machines could write poetry that a human would appreciate. In the course of this quest, he has learnt many things about how poetry works, the limitations of machines and what makes our brains so special, the way people appreciate poetry and various ways in which machines scare them.

Charla de Pablo Gervás en la Semana Complutense de las Letras 2013

Charla impartida por Pablo Gervás durante la Semana Complutense de las Letras (abril 2013), titulada "Protagonismo y autoría en ficción interactiva", donde desarrolló un pequeño recorrido por los mecanismos básicos de la ficción interactiva, centrándose en particular en cómo se utilizan para potenciar la ilusión de protagonismo que se produce en el lector y en cómo pueden llegar a reducir el margen de maniobra del autor a la hora de controlar su propia obra.

Colaboración de personas con dislexia para un estudio sobre accesiblidad

Soy Susana Bautista, estudiante de Doctorado en el grupo, y voy a realizar una colaboración con la Universitat Pompeu Fabra en Barcelona para realizar un experimento para mi tesis. Si conocéis a alguien que pueda participar, no dudéis en poneros en contacto conmigo (subautis@fdi.ucm.es). ¡Gracias! Más información here

Research visit by a group of ENS Cachan students

On Monday 31st January, our Faculty has received the visit of a group of ENS Cachan students. They came from Paris to known about the research we are doing here.

Federico Peinado gave them a talk about Language, Storytelling and Videogames, presenting our research group and his own work in the field.

Merci beaucoup for your visit, folks!

UCM/MIT Indications, Referring Expressions, and Coreference Corpus available

The UMIREC corpus, ellaborated in collaboration with the Genesis research group at MIT, is publicly available. This corpus comprises 62 files in English (30 folktales and 32 Wall Street Journal articles) annotated with the location of referring expressions, coreference relations between the referring expressions, and the descriptive and distinctive information associated to the referring expressions.

Pablo Gervás presenta su colaboración en el libro "¿Puede un computador escribir un poema de amor?” en el Centro Blanquerna

Pablo Gervás ha colaborado en la redacción del libro "¿Puede un computado escribir un poema de amor?" junto a Dionisio Cañas y Carlos González Tardón. La presentación tuvo lugar el martes de 13 de abril del 2010 en el Centro Cultural Blanquerna.

Pages

Subscribe to Natural Interaction based on Language RSS