Investigation of the Morphological and Root Structure of the Arabic Language Structure Using Python

Öz

In the last years, scientists in computer and software have made successful studies in almost every field. Especially in the classification and comparison of optimization algorithms, metaheuristic optimization techniques can be generally classified as population-based and trajectory-based methods. These algorithms are quite suitable for high-dimensional problems and exhibit strong discovery capabilities. The algorithms use a single solution and iteratively improve it based on mathematical models or heuristics. Arabic is a language of derivation with a very rich derivational morphology, with virtually all words originating from roots through patterns. It is a language with numerous inflections and a complicated morphological structure. Arabic plurals used in modern Arabic are listed. Arabic is becoming a significant topic because of applications for information retrieval and natural language processing. There are two types of Arabic plurals: regular and irregular. The standard form also includes masculine and feminine versions. Stemming is a method used in information retrieval to differentiate between single and plural nouns by eliminating the corresponding affixes from words. In this study, we describe a technique that does not rely on stemming to recognize Arabic plurals. Based on the threefold relationship between word, root, and pattern, we utilize both the word and the pattern to find the correct root and the pattern used to define the type of plural. The algorithm has only been provided the fundamental patterns of plurals, whether regular or irregular; the remaining patterns are constructed programmatically to add the appropriate plugins for each type of plural. Finally, since irregular inclusion and humiliation are not governed by direct laws, we get positive outcomes in both cases. In the situation of irregular inclusion and humiliation, we are largely satisfied. Although generally faster, these methods may experience problems such as premature convergence or being stuck in local optima. Recent research has focused on improving existing algorithms by hybridization, parameter tuning, and incorporating additional mechanisms such as chaos theory and adversarial learning.

Anahtar Kelimeler

• Arabic Plurals
• Arabic Morphology
• Root
• Pattern
• Stemming

Kaynakça

1. [1] Q. Yaseen and I. Hmeidi, “Extracting the roots of Arabic words without removing affixes,” Journal of Information Science, vol. 40, no. 3, pp. 376–385, 2014.
2. [2] R. Kanaan and G. Kanaan, “An improved algorithm for the extraction of triliteral Arabic roots,” European Scientific Journal, vol. 10, no. 3, 2014.
3. [3] M. El-Defrawy, N. A. Belal, and Y. El-Sonbaty, “An efficient rank based Arabic root extractor,” 2017 Intelligent Systems Conference (IntelliSys), pp. 870–878, 2017.
4. [4] A. Abu-Errub, A. Al-Ayyoub, Y. Jararweh, and B. Gupta, “Arabic roots extraction using morphological analysis,” International Journal of Computer Science Issues (IJCSI), vol. 11, no. 2, p. 128, 2014.
5. [5] S. Ellouze, K. Haddar, and A. Abdelwahed, “NooJ disambiguation local grammars for Arabic broken plurals,” Proceedings of the NooJ 2010 International Conference, pp. 62–72, 2010.
6. [6] I. Damaj, M. Imdoukh, and R. Zantout, “Parallel hardware for faster morphological analysis,” Journal of King Saud University - Computer and Information Sciences, vol. 30, no. 4, pp. 531–546, 2018.
7. [7] W. Etaiwi and A. Awajan, “Graph-based Arabic NLP techniques: A survey,” Procedia Computer Science, vol. 142, pp. 328–333, 2018.
8. [8] A. Himmah and R. Wahyudi, “A contrastive analysis of Arabic and English noun plural markers,” PAROLE: Journal of Linguistics and Education, vol. 4, no. 2, pp. 72–87, 2014.

9. [9] A. Shafah, T. Ould-Brahim, A. Al-Ayyoub, Y. Jararweh, and B. Gupta, “Irregular Arabic plurals recognition without stemming,” In: 2016 4th International Conference on Control Engineering & Information Technology (CEIT). IEEE, pp. 1–6, 2016.
10. [10] T. Kanan, Y. Kanaan, A. Alsmadi, and M. Hawashin, “Arabic light stemming: A comparative study between p-stemmer, khoja stemmer, and light10 stemmer,” 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 511–515, 2019.
11. [11] I. A. Asadi and A. Khateb, “Predicting reading in vowelized and unvowelized Arabic script: An investigation of reading in first and second grades,” Reading Psychology, vol. 38, no. 5, pp. 486–505, 2017.
12. [12] M. Goudjil, M. Ennaji, and A. Guessoum, “Arabic text categorization using SVM active learning technique: An overview,” 2013 World Congress on Computer and Information Technology (WCCIT), pp. 1–2, 2013.
13. [13] A. H. Krea, A. S. Ahmad, and K. Kabalan, “Arabic words stemming approach using Arabic WordNet,” International Journal of Data Mining & Knowledge Management Process, vol. 4, no. 6, p. 1, 2014.
14. [14] M. N. Al-Kabi, A. A. Al-Ayyoub, Y. Jararweh, and A. A. Huneiti, “A novel root based Arabic stemmer,” Journal of King Saud University - Computer and Information Sciences, vol. 27, no. 2, pp. 94–103, 2015.
15. [15] A. Gowedar, K. R. Beesley, and L. Karttunen, “Identifying broken plurals in unvowelised Arabic text,” Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp. 246–253, 2004.
16. [16] M. Gridach and N. Chenfour, “Developing a new approach for Arabic morphological analysis and generation,” arXiv preprint arXiv:1101.5494, 2011.
17. [17] R. Sonbol, N. Ghneim, and M. S. Desouki, “Arabic morphological analysis: A new approach,” 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, pp. 1–6, 2008.
18. [18] W. Salloum and N. Habash, “ADAM: Analyzer for dialectal Arabic morphology,” Journal of King Saud University - Computer and Information Sciences, vol. 26, no. 4, pp. 372–378, 2014.
19. [19] A. M. Bashir, M. Q. Abughofa, A. M. Kanaan, and M. Z. Rehman, “Implementation of a neural natural language understanding component for Arabic dialogue systems,” Procedia Computer Science, vol. 142, pp. 222–229, 2018.
20. [20] T. Kanan, A. Alsmadi, and M. Hawashin, “A review of natural language processing and machine learning tools used to analyze Arabic social media,” 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), pp. 622–628, 2019.
21. [21] E. Issa, “An OpenNMT model to Arabic broken plurals,” Proceedings of the First International Workshop on Language Cognition and Computational Models, pp. 22–30, 2018.
22. [22] A. Alnaied, M. Elbendak, and A. Bulbul, “An intelligent use of stemmer and morphology analysis for Arabic information retrieval,” Egyptian Informatics Journal, 2020.
23. [23] A. A. Neme and E. Laporte, “Pattern-and-root inflectional morphology: the Arabic broken plural,” Language Sciences, vol. 40, pp. 221–250, 2013.