Developemnt and Evaluation of A Web Based Question Answering System for Arabic Languag

Abstract

Question Answering (QA) systems are gaining great importance due to the increasing amount of web content and the high demand for digital information that regular information retrieval techniques cannot satisfy. A question answering system enables users to have a natural language dialog with the machine, which is required for virtually all emerging online service systems on the Internet. The need for such systems is higher in the context of the Arabic language. This is because of the scarcity of Arabic QA systems, which can be attributed to the great challenges they present to the research community,including theparticularities of Arabic, such as short vowels, absence of capital letters, complex morphology, etc. In this paper, we report the design and implementation of an Arabic web-based question answering system,which we called "JAWEB", the Arabic word for the verb "answer". Unlike all Arabic questionanswering systems, JAWEB is a web-based application,so it can be accessed at any time and from anywhere. Evaluating JAWEBshowed that it gives the correct answer with 100% recall and 80% precision on average. When comparedto ask.com, the well-established web-based QA system, JAWEBprovided 15-20% higher recall.These promising results give clear evidence that JAWEB has great potential as a QA platform and is much needed by Arabic-speaking Internet users across the world.

Arabic Question Answering Systems: Gap Analysis

“…Experiments were conducted on the NER module, question classification module, and overall system performance on 59 questions evaluated manually by five Quranic experts. Kurdi et al[45] proposed an Arabic QA system, named JAWEB, which aims to answer factoid questions ("who," "what," "where," and "when"). JAWEB consists of the three components of QA.…”

“…The highest recall measure among all the systems was 100%, which was achieved by two QA systems. The first was the open-domain factoid QA system JAWEB[45], which did not specify the number of QA pairs experimented on but implemented QE and question classification. The second was a hybrid QA system[33] that experimented with 43 open-domain QA pairs without QE and question classification.…”

“…The maximum precision and MRR measures (97.3% and 86%, respectively) were reached by QARAB [30], which experimented with 113 open-domain QA pairs. The maximum recall (100%) was reached by JAWEB[45], the maximum F1-measure (78.89%) was reached by AQuASys[40], and the maximum AQ measure (68.62%) was reached in[44]. The minimum accuracy, AQ, and MRR measures (22.2%, 47.66%, and 8.16%, respectively) were reached by AlQuAnS[52], which experimented with 200 open-domain QA pairs.…”