Answer Clustering and Fusion in a User-Interactive Question Answering System

Project: Research

View graph of relations



In this project, the need for answer clustering and fusion in a user-interactive question answering (QA) system is identified and its user interface and enabling technology are presented. 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 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.


Project number7002137
Grant typeSRG
Effective start/end date1/04/0728/10/09