Agent-Oriented Language Engineering for Robust NLP

摘要

The main goal of our work is to propose an agent-oriented framework for developing robust NLP applications. This framework provides means to compose analysis modules in a co-operative style. The idea is to encapsulate existing analysis tools and resources within software agents coordinated at a higher level using meta-knowledge. Agents can be activated concurrently and they should provide their linguistic competence depending on the application needs. The activation policy is determined by the context, by the domain knowledge and by performance constraints. At this level, co-ordination is computational logic-based in order to exploit known inference mechanisms for the decision support. This framework should be general enough to cope with other kinds of information sources, such as multimedia documents and with multi-modal dialogue systems.