Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
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. | Utilizing Co-Occurrence of Answers in Question Answering Min Wu1 and Tomek Strzalkowski1 2 1 ILS Institute University at Albany State University of New York 1400 Washington Ave SS261 Albany NY 12222 2Institute of Computer Science Polish Academy of Sciences minwu@cs.albany.edu tomek@csc.albany.edu 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. 1 Introduction Question answering of a series of questions on one topic has gained more and more research interest in the recent years. The current TREC QA test set contains factoid and list questions grouped into different series where each series has the target of a definition associated with it Overview of the TREC 2004 Question Answering Track Voorhees 2005 . Usually the target is also called topic by QA researchers. One of the restrictions of TREC QA is that questions within a series must be processed in order without looking ahead. That is systems are allowed to use answers to earlier questions to help answer later questions in the same series but can not use later questions to help answer earlier questions. This requirement models the dialogue discourse between the user and the QA system. However our experiments
