Title :
Lexical categorical disambiguation using a multi-agent systems architecture
Author :
Da Silva, João Luís Tavares ; De Lima, Vera Lúcia Strube
Author_Institution :
Inst. de Inf., Pontificia Univ. Catolica do Rio Grande do Sul, Terreo Porto Alegre, Brazil
Abstract :
We present a distributed architecture model for lexical categorical disambiguation based on multi agent systems. This proposal aims to minimize some shortcomings from sequential approaches to natural language processing systems, through cooperation among intelligent and distributed modules. We have proposed a model for a linguistic society of agents which includes linguistic knowledge as well as a set of procedures to manipulate it, and mechanisms for social reasoning. The disambiguation is solved by a subsociety of acquaintance agents that use a communication protocol based on cooperative learning in order to reach a common goal
Keywords :
computational linguistics; cooperative systems; inference mechanisms; learning (artificial intelligence); natural languages; software agents; NLP; acquaintance agents; common goal; communication protocol; cooperative learning; distributed architecture model; distributed modules; lexical categorical disambiguation; linguistic knowledge; linguistic society; multi agent systems; natural language processing systems; social reasoning; Communication system control; Message passing; Multiagent systems; Natural language processing; Open systems; Proposals; Protocols; Read only memory; Societies;
Conference_Titel :
Multi Agent Systems, 1998. Proceedings. International Conference on
Conference_Location :
Paris
Print_ISBN :
0-8186-8500-X
DOI :
10.1109/ICMAS.1998.699241
