期刊名称:International Journal of Computer Science and Network Security
印刷版ISSN:1738-7906
出版年度:2006
卷号:6
期号:3A
页码:146-153
出版社:International Journal of Computer Science and Network Security
摘要:One of the major and crucial difficulties in Question Answering (QA) consists in reducing the gap between question and answer to pair them. In this perspective, Question Classification (QC) appears as an important module as it indicates the answer type from the question semantic. The paper present the particularities of our question classification, based on the use of linguistic knowledge and machine learning approaches. Different classification features and multiple classifier combination method are exploited. By using compositive statistic and rule classifiers, and by introducing dependency structure from Minipar and linguistic knowledge from WordNet into question representation, the research shows high accuracy in question classification.