Utilizing co-occurrence of answers in question answering

Abstract

In this paper, we discuss how to utilize the co-occurrence of answers in building an automatic question answering system that answers a series of questions on a specific topic in a batch mode. Experiments show that the answers to the many of the questions in the series usually have a high degree of co-occurrence in relevant document passages. This feature sometimes can't be easily utilized in an automatic QA system which processes questions independently. However it can be utilized in a QA system that processes questions in a batch mode. We have used our pervious TREC QA system as baseline and augmented it with new answer clustering and co-occurrence maximization components to build the batch QA system. The experiment results show that the QA system running under the batch mode get significant performance improvement over our baseline TREC QA system. © 2006 Association for Computational Linguistics.