期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：87
期号：2
出版社：Journal of Theoretical and Applied
摘要：Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying users question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are "Who", "Where" and "What". The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze "What" question and label the questions with "definition", "person", "location" or "object". The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2%, 84.6%, and 83.6% respectively for "Who", "Where" and "What". The result show that the SVM classifier is useful to classify question in Arabic language.
