Authors : Jaffar Atwan and Masnizah Mohd
Abstract: Finding a quick and efficient Query Expansion (QE) technique for all languages has become an urgent necessity because there is no query expansion technique that fully meets user’s requirement. Each technique has its own advantages and disadvantages due to the differences in the languages spoken throughout the world and the vast developments occurred on World Wide Web. Focussing on Arabic, the main problems facing QE are term conflation, stemming and lemmatization and word sense disambiguation. Thus, the purpose of this study is to shed light on some of the techniques that employ Arabic QE available in literature and to encourage researchers to study these techniques. This study focuses on and summarizes the major techniques used in query expansion for Arabic information retrieval and discusses their strengths and weaknesses. It begins with some of the linguistic characteristics of the Arabic language the features of Arabic that are related to query expansion and the possible difficulties that they might present. Researchers concludes by offering suggestions for future research which of these approaches might be suitable for dealing with the specific features of the Arabic language.
Jaffar Atwan and Masnizah Mohd, 2017. Arabic Query Expansion: A Review. Asian Journal of Information Technology, 16: 754-770.