%0 Journal Article
%T Dependency Relation Triples Matching for Question Answering<br>依赖关系三元组匹配在问题回答中的应用
%A LIN Feng
%A ZHOU Ya-Qian
%A HUANG Xuan-Jing
%A WU Li-De
%A <br>林锋
%A 周雅倩
%A 黄萱菁
%A 吴立德
%J 自动化学报
%D 2008
%I 
%X This paper presents a new method to compute the similarity between question and answer sentences, namely dependency relation triples matching. This method considers the information of question s interrogative part and non- interrogative part, and heuristic rules are used to expand question s relation triples to match metamorphosing answer sentences. Then, this similarity score is used as a new feature for answer ranking in open domain question answering (QA) track. The experiments show the new answer ranking method outperforms the common density-based approach by up to 8.2% in relative precision and 8% in mean reciprocal rank (MRR) evaluation.
%K Question answering
%K answering ranking
%K dependency relation triple<br>问题回答
%K 答案排序
%K 依赖关系三元组
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=09F5EC0866ED55A581280A8C19BB2B5E&yid=67289AFF6305E306&vid=339D79302DF62549&iid=708DD6B15D2464E8&sid=3FD5B2D1B84CE43E&eid=B240D359488D2362&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=9