An Arabic Question-Answering System Combining a Semantic and Logical Representation of Texts

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 736)

Abstract

In this paper, we present the overall structure of our specific system for generating answers of questions in Arabic, named NArQAS (New Arabic Question Answering System). This system aims to develop and evaluate the contribution of the use of reasoning procedures, natural language processing techniques and the recognizing textual entailment technology to develop precise answers to natural language questions. We also detail its operating architecture. In particular, our system is seen as a contribution, rather than a rival, to traditional systems focused on approaches extensively used information retrieval and natural language processing techniques. Thus, we present the evaluation of the outputs of each of these components based on a collection of questions and texts retrieved from the Web. NArQAS system was built and experiments showed good results with an accuracy of 68% for answering factual questions from the Web.

Keywords

NArQAS Question-answering system Arabic Architecture Logic representation Implementation Evaluation 

References

  1. 1.
    Bakari, W., Trigui, O., Neji, M.: Logic-based approach for improving Arabic question answering. In: 2014 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1–6. IEEE, December 2014Google Scholar
  2. 2.
    Bakari, W., Bellot, P., Neji, M.: AQA-WebCorp: web-based factual questions for Arabic. Procedia Comput. Sci. 96, 275–284 (2016)CrossRefGoogle Scholar
  3. 3.
    Bakari, W., Bellot, P., Neji, M.: Literature review of Arabic question-answering: modeling, generation, experimentation and performance analysis. In: FQAS, pp. 321–334 (2015)Google Scholar
  4. 4.
    Bakari, W., Bellot, P., Neji, M.: Researches and reviews in Arabic question answering: principal approaches and systems with classification (2016)Google Scholar
  5. 5.
    Bakari, W., Bellot, P., Trigui, O., Neji, M.: Towards logical inference for the Arabic question-answering (2015)Google Scholar
  6. 6.
    Bakari, W., Bellot, P., Neji, M.: A preliminary study for building an Arabic corpus of pair questions-texts from the web: AQA-WebCorp. iJES 4(2), 38–45 (2016)Google Scholar
  7. 7.
    Al-Khalifa, H., Al-Wabil, A.: The Arabic language and the semantic web: challenges and opportunities. In: The 1st International Symposium on Computer and Arabic Language (2007)Google Scholar
  8. 8.
    Olvera-Lobo, M.D., Gutiérrez-Artacho, J.: Question answering track evaluation in TREC, CLEF and NTCIR. In: New Contributions in Information Systems and Technologies, pp. 13–22. Springer (2015)Google Scholar
  9. 9.
    Chavan, G., Gore, S.: Design of the effective question answering system by performing question analysis using the classifier. Int. J. Comput. Appl. 139(14), 1–3 (2016)Google Scholar
  10. 10.
    Al Agha, I., Abu-Taha, A.: AR2SPARQL: an Arabic natural language interface for the semantic web. Int. J. Comput. Appl. 125(6), 19–27 (2015)Google Scholar
  11. 11.
    Cheddadi, A.: Three-levels Approach for Arabic Question Answering Systems. Diss. Ecole Mohammadia d’Ingénieurs (2014)Google Scholar
  12. 12.
    Sowa, J.F.: Conceptual Structures: Information Processing in Mind and Machine. Addison-Wesley, Reading (1984)MATHGoogle Scholar
  13. 13.
    Moldovan, D., Harabagiu, S., Girju, R., Morarescu, P., Novischi, A., Lacatusu, F., Badulescu, A., Bolohan, O.: LCC tools for question answering. In: Voorhees, E., Buckland, L. (eds.) Proceedings of TREC 2002 (2002)Google Scholar
  14. 14.
    Voorhees, E.: Overview of the TREC 2002 question answering track. In: TREC 2002 (2002). http://trec.nist.gov

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Faculty of Economics and ManagementSfaxTunisia
  2. 2.MIR@CLSfaxTunisia

Personalised recommendations