摘要
本文提出了一种用于受限领域自动问答的新方法。与传统的自动问答方法不同,该方法不对用户问题进行语言分析以生成结构化的查询,而是利用文本蕴涵技术从自动生成的假设问题库中寻找用户问题所蕴涵的假设问题,然后利用该假设问题所附的答案指南获取用户问题的答案。该方法的优点之一是不需要复杂的语言处理就可以回答复杂的问题,而且正确率较高;优点之二是可以利用本体方便地生成不同语种的假设问题,实现跨语言问答。本文基于英文提问对该方法进行了测评,测评结果表明几乎所有的用户问题都可以基于生成的假设问题来直接或间接地回答,回答的正确率达到65.6%。
This paper presents a new knowledge-based Question Answering（QA）method for a restricted domain with the use of textual entailment.In this method,a set of question patterns,called hypothesis questions,was automatically produced from a domain ontology,along with their corresponding query templates for answer retrieval.Then the QA task was reduced to the problem of looking for the hypothesis question that was entailed by a user question and taking its corresponding query template to produce a complete query for retrieving the answers from underlying knowledge bases.This method is able to answer complex questions without involving complex language processing and can be easily ported to other languages.An evaluation was carried out to assess the accuracy of the QA method,and the results revealed that almost all the user questions can be answered directly or indirectly based on the produced hypothesis questions,and the QA accuracy is 65.6%with the use of a semantic entailment engine enhanced by the domain ontology.
出处
《情报学报》
CSSCI
北大核心
2011年第5期540-547,共8页
Journal of the China Society for Scientific and Technical Information
基金
欧盟研究项目QALL-ME（FP6 IST-033860 at http：//qallme.fbk.eu）的资助
关键词
自动问答
文本蕴涵
本体
question answering
textual entailment
ontology
