Towards the Construction of a Multi-agent Approach for Discovering the Meaning of Natural Language Collaborative Conversations

On the one hand, natural language is the main communication media for humans. It has a complex construction, based on the diversity of meaning for words and expressions according to the context. On the other hand, computers are not prepared to handle this ambiguity. The present work aims at presenting a multi-agent approach for dealing with the problem of discovering the meaning of expressions written in Spanish, based on a flexible recovery system and Bayesian principles. At a first stage, agents are supposed to identify the role of the words composing a sentence. At a second stage, a second set of agents is supposed to coordinate among them in order to assemble a meaning. Our research forms part and contributes to the analysis of collaborative conversations among participants in a web-based collaborative learning environment.