Inference-Driven Semantic Analysis

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 3

Natural Language

A primary problem in the area of natural language processing is the problem of semantic analysis, This involves both formalizing the general and domain-dependent semantic information relevant to the task involved, and developing a uniform method for access to that information. Natural language interfaces are gen-erally also required to have access to the syntactic analysis of a sentence as well as knowledge of the prior discourse to produce a semantic representation ade-quate for the task. This paper briefly describes previous approaches to semantic analysis, specifically those approaches which can be described as using templates, and corresponding multiple levels of representation. It then presents an alternative to the template approach, inference-driven semantic analysis, which can perform the same tasks but without needing as many levels of representation.