Answer Clustering and Fusion in a User-Interactive QA System

The need of answer clustering and fusion in a user-interactive question answering (QA) system is identified and its user interface and enabling technology are presented in this paper. This function aims to help a user to efficiently browse all the answers and find the correct answer to a specific question by clustering answers into groups and providing a representative (fused) answer for each group. The clustering approach proposed in this paper includes a measurement of semantic similarity between answers and an incremental soft-moVMF algorithm. An answer fusion method is proposed, which uses concept vector and authority of data sources to extract the summary for the answers in each cluster. Experiments and user studies show that the UI and the methods are effective.