Paper: A Data Driven Approach To Relevancy Recognition For Contextual Question Answering

ACL ID W06-3005
Title A Data Driven Approach To Relevancy Recognition For Contextual Question Answering
Venue Interactive Question Answering Workshop
Session
Year 2006
Authors

Contextual question answering (QA), in which users’ information needs are satis- fied through an interactive QA dialogue, has recently attracted more research atten- tion. One challenge of engaging dialogue into QA systems is to determine whether a question is relevant to the previous inter- action context. We refer to this task as rel- evancy recognition. In this paper we pro- pose a data driven approach for the task of relevancy recognition and evaluate it on two data sets: the TREC data and the HandQA data. The results show that we achieve better performance than a previ- ous rule-based algorithm. A detailed eval- uation analysis is presented.