An arabic question classification method based on new taxonomy and continuous distributed representation of words

Abstract

The unability of search engines to retrieve precise answer for a given question leads research teams to build question answering systems (QAS). These systems provide exact answers of questions formulated in natural languages. Question classification is a crucial task for QAS since finding the correct answer type increases the performance of this latter. The questions taxonomy plays an important role in question classification. A broad range of taxonomies are proposed; most of these are not designed for Arabic questions. The contribution of the paper is twofold. First, we build a taxonomy for open domain Arabic questions. Second, we propose an efficient method for classifying Arabic questions. The basic idea consists of two stages: first, we compute representation of questions according to continuous distributed representation of words which allows to capture syntactic and semantic relations between words. Then, we apply a machine learning approach to classify questions into seven types or categories. We carried out several experiments and compared the proposed method with different state of arts Arabic question classification methods. Experimental results show that the proposed method achieves 90% in terms of accuracy.