Japanese Question-Answering System Using Decreased Adding with Multiple Answers at NTCIR 5.
Masaki Murata, Masao Utiyama, Hitoshi Isahara · NTCIR · 2005
We propose a new method of using multiple documents with decreasing weights as evidence to improve the performance of a question-answering system. Sometimes, the answer to a question may be found in multiple documents. In such cases, using multiple documents for prediction would generate better answers than using a single document. Thus, our method employs information from multiple documents by adding the scores of the candidate answers extracted from the various documents. Because simply adding scores degrades the performance of questionanswering systems, we add scores with decreasing weights to reduce the negative effect of simple adding. We used this method at NTCIR 4 and NTCIR 5, where it obtained very good results. The three systems that we submitted to NTCIR 5 obtained the highest scores among the 16 systems that participated in the conference.