Multimedia Question Answering System

Over the past year Community question answering (cQA) services have Achieved popularity. It allow members to post and answer questions as enables general users to seek information from comprehensive set of well-answered questions. But Still, existing cQA forums usually only provide textual answers, for many questions which are not informative enough. In this paper, we propose a schema that is able to enrich textual answers in CQA with Appropriate media data. For multimedia search, and multimedia data selection and presentation our scheme consists of three components: answer medium selection, question base classification ,query generation, MM data selection and presentation. This method automatically decides which type of media information should be added for textual answer. It then automatically gathers data from the web. Our approach can enable a novel multimedia question answering (MMQA) approach by processing large set of QA pairs and adding them to the pool. users can find multimedia answers by matching their questions with those in a pool. Our approach is based on community-contributed textual answers and thus it is able to deal with more complex questions.