International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Using Roots and Patterns to Detect Arabic Verbs without Affixes Removal

  • Abdulmonem Ahmed (Department of Material Science and Engineering, Graduate School of Natural and Applied Kastamonu University) ;
  • Aybaba Hancrliogullari (Department of Physics, Faculty of Science and Letters, Kastamonu University) ;
  • Ali Riza Tosun (Department of Philosophy, Faculty of Science and Letters, Kastamonu University)
  • Received : 2023.04.05
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Morphological analysis is a branch of natural language processing, is now a rapidly growing field. The fundamental tenet of morphological analysis is that it can establish the roots or stems of words and enable comparison to the original term. Arabic is a highly inflected and derivational language and it has a strong structure. Each root or stem can have a large number of affixes attached to it due to the non-concatenative nature of Arabic morphology, increasing the number of possible inflected words that can be created. Accurate verb recognition and extraction are necessary nearly all issues in well-known study topics include Web Search, Information Retrieval, Machine Translation, Question Answering and so forth. in this work we have designed and implemented an algorithm to detect and recognize Arbic Verbs from Arabic text.The suggested technique was created with "Python" and the "pyqt5" visual package, allowing for quick modification and easy addition of new patterns. We employed 17 alternative patterns to represent all verbs in terms of singular, plural, masculine, and feminine pronouns as well as past, present, and imperative verb tenses. All of the verbs that matched these patterns were used when a verb has a root, and the outcomes were reliable. The approach is able to recognize all verbs with the same structure without requiring any alterations to the code or design. The verbs that are not recognized by our method have no antecedents in the Arabic roots. According to our work, the strategy can rapidly and precisely identify verbs with roots, but it cannot be used to identify verbs that are not in the Arabic language. We advise employing a hybrid approach that combines many principles as a result.

Keywords

References

  1. Ameur, Mohamed Seghir Hadj, Farid Meziane, and Ahmed Guessoum. "Arabic machine translation: A survey of the latest trends and challenges." Computer Science Review 38 (2020): 100305.
  2. Guellil, Imane, et al. "Arabic natural language processing: An overview." Journal of King Saud University-Computer and Information Sciences 33.5 (2021): 497-507. https://doi.org/10.1016/j.jksuci.2019.02.006
  3. Alkhatib, Manar, and Khaled Shaalan. "The key challenges for Arabic machine translation." Intelligent Natural Language Processing: Trends and Applications. Springer, Cham, 2018. 139-156.
  4. Habash, Nizar, and Fatiha Sadat. "Arabic preprocessing schemes for statistical machine translation." Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers. 2006.
  5. Tahat, Abdelrazzaq. "Morphological Patterns of Personal Naming Practice: A Case Study of Non-Concatenative Arabic Language." (2020).
  6. Zayed, O. H., & El-Beltagy, S. R. (2012, May). Person name extraction from modern standard Arabic or colloquial text. In 2012 8th International Conference on Informatics and Systems (INFOS) (pp. NLP-44). IEEE.
  7. Abdallah, S., Shaalan, K., & Shoaib, M. (2012, March). Integrating rule-based system with classification for arabic named entity recognition. In International Conference on Intelligent Text Processing and Computational Linguistics (pp. 311-322). Springer, Berlin, Heidelberg.
  8. Mansouri, A., Affendey, L. S., & Mamat, A. (2008). Named entity recognition using a new fuzzy support vector machine. IJCSNS, 8(2), 320.
  9. Chiu, J. P., & Nichols, E. (2016). Named entity recognition with bidirectional LSTM-CNNs. Transactions of the association for computational linguistics, 4, 357-370. https://doi.org/10.1162/tacl_a_00104
  10. Alasmari, Jawharah, Janet CE Watson, and Eric Atwell. "A comparative analysis of verb tense and aspect in Arabic and English using Google Translate." International Journal on Islamic Applications in Computer Science and Technology 5.3(2017): 9-13.
  11. Shaalan, Khaled, Marwa Magdy, and Aly Fahmy. "Analysis and feedback of erroneous Arabic verbs." Natural Language Engineering 21.2 (2015): 271-323. https://doi.org/10.1017/S1351324913000223
  12. Ray, Santosh K., and Khaled Shaalan. "A review and future perspectives of arabic question answering systems." IEEE Transactions on Knowledge and Data Engineering 28.12(2016): 3169-3190. https://doi.org/10.1109/TKDE.2016.2607201
  13. Muhammed, Muhammed H., Bassim M. Salih, and Omer K. Jasim. "An Emerging Standard Miniaturization in Arabic Morphological Analysis." 2018 1st Annual International Conference on Information and Sciences (AiCIS). IEEE, 2018.
  14. Mourad Gridach and Noureddine Chenfour, Developing a New Approach for Arabic Morphological Analysis and Generation, International Joint Conference on Natural Language Processing,Vol.2, 2011.
  15. Mohammed Attia, Pavel Pecina, Antonio Toral, Lamia Tounsi and Josef van Genabith, An Open-Source Finite State Morphological Transducer for Modern Standard Arabic, FSMNLP '11 Proceedings of the 9th International Workshop on Finite State Methods and Natural Language Processing, 2011.
  16. AbdelRahim A. Elmadany, Sherif M. Abdou and Mervat Gheith, A Survey of Arabic Dialogues Understanding for Spontaneous Dialogues and Instant Message, International Journal on Natural Language Computing (IJNLC) Vol. 4, No.2, 2015.
  17. A. FARGHALY and K. SHAALAN, Arabic Natural Language Processing: Challenges and Solutions, ACM Trans. Asian Language Information Processing, Vol. 8 No. 4, 2009.
  18. Alshalabi, H., Tiun, S., Omar, N., & Albared, M. (2013). Experiments on the use of feature selection and machine learning methods in automatic malay text categorization. Procedia Technology, 11, 748-754. https://doi.org/10.1016/j.protcy.2013.12.254
  19. Alkhudair, Raghad, and Mohammad Aljutaily. "A prosodic morphophonological analysis of the trilateral perfect passive verbs in Qassimi Arabic." Heliyon 8.8 (2022): e10008.
  20. Azman, Bakeel. "Root identification tool for Arabic verbs." IEEE Access 7 (2019): 45866-45871. https://doi.org/10.1109/ACCESS.2019.2908177
  21. Kambhatla, Nandakishore, and Imed Zitouni. "Systems and methods for automatic semantic role labeling of high morphological text for natural language processing applications." U.S. Patent No. 8,527,262. 3 Sep. 2013.
  22. Ramadhan, Teguh Ikhlas, Moch Arif Bijaksana, and Arief Fatchul Huda. "Rule based pattern type of verb identification algorithm for the holy qur'an." Procedia Computer Science 157 (2019): 337-344. https://doi.org/10.1016/j.procs.2019.08.175
  23. N. Habash, ''Arabic morphological representations for machine translation,'' Arabic Computational Morphology. Springer, 2007, pp. 263-285.
  24. Boudchiche, M., & Mazroui, A. (2018, April). Improving the Arabic root extraction by using the quadratic splines. In 2018 International Conference on Intelligent Systems and Computer Vision (ISCV) (pp. 1-5). IEEE.
  25. Yousfi, A. "The morphological analysis of Arabic verbs by using the surface patterns." IJCSI International Journal of Computer Science Issues 7.3 (2010): 11.
  26. Hegazi, M. O., Al-Dossari, Y., Al-Yahy, A., Al-Sumari, A., & Hilal, A. (2021). Preprocessing Arabic text on social media. Heliyon, 7(2), e06191.
  27. El-Affendi, Mohammed Ahmed. "An LVQ connectionist solution to the non-determinacy problem in Arabic morphological analysis: a learning hybrid algorithm." Natural Language Engineering 8.1 (2002): 3-23. https://doi.org/10.1017/S1351324901002753
  28. Shrestha, B. B., & Bal, B. K. (2020, December). Named-entity based sentiment analysis of Nepali news media texts. In Proceedings of the 6th workshop on natural language processing techniques for educational applications (pp. 114-120).
  29. Almusaddar, M., 2014. Improving Arabic Light Stemming in Information Retrieval Systems. Thesis MSC Thesis. Computer Engineering Department, Faculty of Engineering, Research and Postgraduate Affairs. Islamic University, Gaza, Palestine
  30. Siswoyo, Siswoyo. "SIMILARITIES AND DIFFERENCES BETWEEN ENGLISH AND ARABIC VERB." Jurnal Smart 2.2 (2016).
  31. Ismail, Samia Ben, Sirine Boukedi, and Kais Haddar. "Transformation system to generate derivational forms of an Arabic verb with HPSG." 2017 International Conference on Engineering & MIS (ICEMIS). IEEE, 2017.
  32. Othman, Mohamed Tahar Ben, Mohammed Abdullah AlHagery, and Yahya Muhammad El Hashemi. "Arabic text processing model: Verbs roots and conjugation automation." IEEE Access 8 (2020): 103913-103923. https://doi.org/10.1109/ACCESS.2020.2999259
  33. Mohammed, Rafea. "New Arabic stemming based on Arabic patterns." Iraqi J. Sci. 57.3 (2016): 2324-2330.
  34. Abd Alameer, A. Q. (2017). Finding the similarity between two Arabic texts. Iraqi Journal of Science, 152-162.
  35. Farghaly, A., & Shaalan, K. (2009). Arabic natural language processing: Challenges and solutions. ACM Transactions on Asian Language Information Processing (TALIP), 8(4), 1-22. https://doi.org/10.1145/1644879.1644881
  36. Alshalabi, H., Tiun, S., Omar, N., AL-Aswadi, F. N., & Alezabi, K. A. (2021). Arabic light-based stemmer using new rules. Journal of King Saud University-Computer and Information Sciences.
  37. Thalji, N., Hanin, N. A., Al-Hakeem, S., Hani, W. B., & Thalji, Z. (2018). A novel rule-based root extraction algorithm for Arabic language. International Journal of Advanced