Exploitation of Query Sentences using Specific Weighting in Support-Sentence Retrieval

摘要

Our goal is to develop a support-sentence retrieval system that retrieves sentences relevant to a given theme and then, classifies them into relevant types, such as agreement, contradiction, refinement, and supplement. This paper focuses on the first step, a sentence retrieval module. Lexical and typed dependency matching are used to compute the similarity between two sentences. A new query term weighting scheme based on the specificity of the terms is proposed and combined with ordinary IDF weighting for a better performance. Experimental results indicate that our method achieves 34% higher precision than the traditional TF-ISF method..