Description

Community question answering (cQA) se rvices have gained popularity over the past years. It not only allows commu-nity members to post and answer qu estions but also enables gen-eral users to seek information from a comprehensive set of well-an-swered questions. However, existing cQA forums usually provide only textual answers, which are not informative enough for many questions. In this paper, we propose a scheme that is able to en-rich textual answers in cQA with appropriate media data. Our scheme consists of three components: answer medium selection, query generation for multimedia sea rch, and multimedia data se-lection and presentation. This app roach automatically determines which type of media information should be added for a textual an-swer. It then automatically co llects data from the web to enrich the answer. By processing a large se t of QA pairs and adding them to a pool, our approach can enable a novel multimedia question an-swering (MMQA) approach as u sers can fi nd multimedia answers by matching their questions with those in the pool. Different from a lot of MMQA research efforts that attempt to directly answer ques-tions with image and vid eo data, our approach is built based on community-contributed textual answers and thus it is able to deal with more complex questions. We have conducted extensive exper-iments on a multi-source QA dataset. The results demonstrate the effectiveness of our approach.