Discourse as a Knowledge Resource for Sentence Disambiguation

Abstract

A consistent text contains rich resources of information such as collocation patterns that can be used to resolve ambiguities within its sentences For example attachment ambiguities in a sentence can be resolved by selecting a candidate attachment that matches attachments found in other sentences in the same discourse Thus, discourse can be regarded as a valuable knowledge resource for sentence analysis In this paper, we examine some features of discourse as a knowledge resource and propose a framework for natural language processing that provides a simple algorithm for using information extracted from discourse together with information stored in knowledge bases The experimental results of using our framework to disambiguate sentences in technical documents offer good prospects for improving the accuracy of a broad coverage natural language processing system that handles various texts without constructing knowledge bases for each text in advance Some noteworthy features of discourse information are also deduced from the results of our experiments.