Abstract | ||
---|---|---|
In this work 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. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/ICMAS.1998.699241 | ICMAS |
Keywords | Field | DocType |
read only memory,multi agent systems,cooperative learning,protocols,multiagent systems,natural language processing,open systems,software agents,learning artificial intelligence,natural languages,communication protocol,nlp,multi agent system,computational linguistics,message passing,distributed architecture | Computer science,Categorical variable,Computational linguistics,Software agent,Multi-agent system,Natural language,Artificial intelligence,Natural language processing,Cooperative learning,Message passing,Communications protocol | Conference |
ISBN | Citations | PageRank |
0-8186-8500-X | 2 | 0.38 |
References | Authors | |
1 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joã L. T. da Silva | 1 | 4 | 1.26 |
Vera Lúcia Strube de Lima | 2 | 106 | 17.97 |
da Silva, J.L.T. | 3 | 2 | 0.38 |
Strube de Lima, V.L. | 4 | 2 | 0.38 |