15th European Conference on Artificial Intelligence
|July 21-26 2002 Lyon France|
Michael Daum, Wolfgang Menzel
In this paper an application of guided local search (GLS) to the problem of natural language parsing is presented. The given parsing approach is situated in a constraint based parsing paradigm that allows natural language processing in a robust and resource adaptive way. Some extensions of GLS are introduced, most notably a multi-threaded search where a couple of agents cooperate with each other in parallel, showing synergetic effects. The resulting algorithm is compared to competing techniques within the framework of weighted constraint dependency grammars. An experimental evaluation shows GLS being on par with similar approaches.
Keywords: Natural Language Processing, Constraint Satisfaction, Search, Meta-Heuristics for AI
Citation: Michael Daum, Wolfgang Menzel: Parsing Natural Language using Guided Local Search. In F. van Harmelen (ed.): ECAI2002, Proceedings of the 15th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2002, pp.435-439.