tailieunhanh - Báo cáo khoa học: "Sentence Dependency Tagging in Online Question Answering Forums"

Online forums are becoming a popular resource in the state of the art question answering (QA) systems. Because of its nature as an online community, it contains more updated knowledge than other places. However, going through tedious and redundant posts to look for answers could be very time consuming. | Sentence Dependency Tagging in Online Question Answering Forums Zhonghua Qu and Yang Liu The University of Texas at Dallas qzh yangl@ Abstract Online forums are becoming a popular resource in the state of the art question answering QA systems. Because of its nature as an online community it contains more updated knowledge than other places. However going through tedious and redundant posts to look for answers could be very time consuming. Most prior work focused on extracting only question answering sentences from user conversations. In this paper we introduce the task of sentence dependency tagging. Finding dependency structure can not only help find answer quickly but also allow users to trace back how the answer is concluded through user conversations. We use linear-chain conditional random fields CRF for sentence type tagging and a 2D CRF to label the dependency relation between sentences. Our experimental results show that our proposed approach performs well for sentence dependency tagging. This dependency information can benefit other tasks such as thread ranking and answer summarization in online forums. 1 Introduction Automatic Question Answering QA systems rely heavily on good sources of data that contain questions and answers. Question answering forums such as technical support forums are places where users find answers through conversations. Because of their nature as online communities question answering forums provide more updated answers to new problems. For example when the latest release of Linux has a bug we can expect to find solutions 554 in forums first. However unlike other structured knowledge bases often it is not straightforward to extract information such as questions and answers in online forums because such information spreads in the conversations among multiple users in a thread. A lot of previous work has focused on extracting the question and answer sentences from forum threads. However there is much richer information