Project information
Abstract: 

This project investigates the potential integration of two Artificial Intelligence domains by investigating the problematic role of syntax within both lines of research. Syntactic research within the subfield of Memory Based Reasoning is concerned with optimising two classification tasks: classification of segmentation (delimiting constituents) and classification of disambiguation (assigning grammatical labels).The robotic experiments that are being conducted within the Origins of Language research at the AI-lab (VUB), can likewise be interpreted as classification experiments. This classification task is problematic in both domains. Joint experiments, in which properties of both MBR and the OoL research will be combined, will try to attribute new insights in both research areas, so that a number of important limitations can be resolved.

Abstract Dutch: 

Dit project verkent de mogelijke integratie van twee sub-disciplines van de Artificiële Intelligentie aan de hand van de problematische rol van syntaxis binnen beide. Het syntactisch onderzoek binnen Memory Based Reasoning spitst zich toe op de optimalisering van twee classificatietaken: classificatie van segmentering (afbakenen van constituenten) en classificatie van desambiguering (toekennen van grammaticale categorieën). De robotische experimenten zoals die door de Origins of Language-onderzoek van het AI-lab van de VUB worden uitgevoerd, kunnen eveneens worden geherinterpreteerd als classificatie-experimenten. In beide domeinen is deze classificatie problematisch. Overkoepelende experimenten, waarin eigenschappen van zowel MBR als het OoL-onderzoek worden gecombineerd, zullen proberen nieuwe inzichten aan te brengen voor beide onderzoeksdomeinen, zodat een aantal belangrijke beperkingen kan worden

Project Leader(s): 
Walter Daelemans
Guy De Pauw
Sponsor(s): 

FWO

Publications + Talks

De Pauw, G. (2006).  Towards a Fixed Word Order in a Society of Agents: a Data-Driven Baseline Perspective. Proceedings of the Sixth International Evolution of Language Conference. 43-50. PDF
De Pauw, G. (2005).  Agent-Based Unsupervised Grammar Induction. Proceedings of the Third European Workshop on Multi-Agent Systems. 114-125.
De Pauw, G. (2004).  A corpus-based natural language grammar optimization approach using agent-based evolutionary computing. Proceedings of the annual machine learning conference of Belgium and The Netherlands. 30-37. PDF
De Pauw, G. (2003).  Evolutionary computing as a tool for grammar development. Genetic and Evolutionary Computation Conference. Proceedings, Part I, pages 549-560. PDF
De Pauw, G. (2003).  GRAEL: an agent-based evolutionary computing approach for natural language. Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. 823-828. PDF
De Pauw, G., & Daelemans W. (2000).  A short introduction to GRAEL grammar adaptation, evolution and learning. Proceedings of the 3rd International Conference on the Evolution of Language. 72-76.
De Pauw, G. (2000).  Aspects of Pattern-Matching in Data Oriented Parsing. Proceedings of the Twelfth Belgium-Netherlands Artificial Intelligence Conference. 333-334.
Syndicate content