Leveraging Arabic morphology and syntax for achieving better keyphrase extraction

Arabic is one of the fastest growing languages on the Web, with an increasing amount of user generated content being published by both native and non-native speakers all over the world. Despite the great linguistic differences between Arabic and western languages such as English, most Arabic keyphrase extraction systems rely on approaches designed for western languages, thus ignoring its rich morphology and syntax. In this paper we present a new approach leveraging the Arabic morphology and syntax to generate a restricted set of meaningful candidates among which keyphrases are selected. Though employing a small set of well-known features to select the final keyphrases, our system consistently outperforms the well-known and established systems.