Domain Adaptation for Bilingual Arabic-English Neural Machine Translation (NMT)

Dalal Abduallah Aljohany; Hassanin M. Al-Barhamtoshy; Felwa Abukhodair; Maysoon Abulkhair

doi:10.26713/cma.v17i2.3662

Authors

Dalal Abduallah Aljohany Faculty of Computing and Information Technology, King Abdulaziz University Jeddah, Abdullah Alsulaiman St., Al-Jamiah, Jeddah 21589, Saudi Arabia https://orcid.org/0009-0003-0763-5009
Hassanin M. Al-Barhamtoshy International Jeddah Collage, Ibn Rasheed Al Fehri, Taiba, Jeddah 23831, Saudi Arabia
Felwa Abukhodair Faculty of Computing and Information Technology, King Abdulaziz University Jeddah, Abdullah Alsulaiman St., Al-Jamiah, Jeddah 21589, Saudi Arabia https://orcid.org/0000-0002-9685-4822
Maysoon Abulkhair Faculty of Computing and Information Technology, King Abdulaziz University Jeddah, Abdullah Alsulaiman St., Al-Jamiah, Jeddah 21589, Saudi Arabia

DOI:

https://doi.org/10.26713/cma.v17i2.3662

Keywords:

Arabic Machine Translation (AMT), Natural Language Processing (NLP), Machine Translation (MT), Neural Machine Translation (NMT), Parallel corpus

Abstract

The importance of Arabic Machine Translation (AMT) cannot be overstated as it seeks to enhance communication between Arabic and non-Arabic speakers. Given that there are an estimated 300 million speakers globally, Arabic is essential for cultural exchanges, global commerce, and diplomatic relations. Nevertheless, what creates substantial obstacles for the Arabic language with regards to Machine Translation (MT) is the fact that it is categorized as a language with low resources as well as one with complex and rich morphological features. Neural Machine Translation (NMT) has emerged as the pinnacle of MT methodologies. Although there exist numerous NMT tools and models designed for translation of Arabic text, the translation quality is often lacking, particularly with texts that fall out-of-domain. A primary technical obstacle associated with AMT stems from the scarcity of bilingual datasets for such texts that are out-of-domain. Consequently, this research seeks to enhance AMT across various domains. To achieve this, we designed a multi-domain parallel corpus specifically for Arabic-English (AR-EN) translation, which was later utilized to train the proposed NMT model. The model uses the encoder–decoder architecture that employs Long Short-Term Memory (LSTM) networks, which are themselves integrated with attention mechanisms. The experimental results show that this proposed model improves accuracy of translation and reduces the loss. To evaluate the efficacy of our proposed NMT model we compared its performance against both OPUS MT system and Google Translate across four domains using BLEU as a metric for assessment. In translations from Arabic to English, our model consistently outperformed both OPUS MT and Google Translate across every domain assessed—averaging +18.66 BLEU points above OPUS MT while exceeding Google Translate by approximately +18.11 BLEU points overall. Similarly consistent superiority was observed in the English to Arabic direction where average gains reached +22.39 points over OPUS MT and +15.36 points over Google Translate.

273 14

Downloads

Download data is not yet available.

References

[1] N. Abdullah, Transfer-based Arabic to English noun sentence translation using shallow segmentation, The International Arab Journal of Information Technology 15(5) (2018), 889 – 893.

[2] E. A. Alghamdi, J. Zakraoui and F. A. Abanmy, Domain adaptation for Arabic machine translation: Financial texts as a case study, Applied Sciences 14(16) (2024), 7088, DOI: 10.3390/app14167088.

[3] A. Almahairi, K. Cho, N. Habash and A. C. Courville, First result on Arabic neural machine translation, arXiv:1606.02680 (2016), 6 pages, DOI: 10.48550/arXiv.1606.02680.

[4] A. T. Al-Taani and E. M. Hailat, A direct English-Arabic machine translation system, Information Technology Journal 4(3) (2005), 256 – 261, DOI: 10.3923/itj.2005.256.261.

[5] W. Aransa, Statistical Machine Translation of the Arabic Language, Ph.D. dissertation, LIUM - Laboratoire d’Informatique de l’Université du Maine, (2015), URL: https://theses.hal.science/tel-01316544v1.

[6] D. Ataman, A. Birch, N. Habash, M. Federico, P. Koehn and K. Cho, Machine translation in the era of large language models: A survey of historical and emerging problems, Information 16(9) (2025), 723, DOI: 10.3390/info16090723.

[7] D. Bahdanau, K. Cho and Y. Bengio, Neural machine translation by jointly learning to align and translate, in: Proceedings of the International Conference on Learning Representations (ICLR’2015, May 7-9, 2015), 15 pages, (2015).

[8] S. Berrichi and A. Mazroui, Guiding word alignment with prior knowledge to improve English-Arabic machine translation, in: BDIoT’19: Proceedings of the 4th International Conference on Big Data and Internet of Things, Article number 9 (2019), pp. 1 – 5, DOI: 10.1145/3372938.3372957.

[9] M. R. Costa-Jussà, M. Farrús, J. B. Mariño and J. A. R. Fonollosa, Study and comparison of rulebased and statistical Catalan-Spanish machine translation systems, Computing and Informatics 31(2) (2012), 245 – 270, URL: https://repositori.upf.edu/server/api/core/bitstreams/8951cb08-54b8-44f9-a0ec-6aa892042218/content.

[10] G. F. Coulouris, J. Dollimore, T. Kindberg and G. Blair, Distributed Systems: Concepts and Design, 5th edition, Addison-Wesely, Boston, xvi + 1047 pages (2012).

[11] H. Daumé III and J. Jagarlamudi, Domain adaptation for machine translation by mining unseen words, in: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 407 – 412, (2011), URL: https://aclanthology.org/P11-2071/.

[12] R. Ehab, English-Arabic hybrid machine translation system using EBMT and translation memory, International Journal of Advanced Computer Science and Applications 10(1) (2019), DOI: 10.14569/IJACSA.2019.0100126.

[13] R. Ehab, E. Amer and M. Gadallah, Example-based English to Arabic machine translation: Matching stage using internal medicine publications, in: ICSIE’18: Proceedings of the 7th International Conference on Software and Information Engineering, (2018), pp. 131 – 135, DOI: 10.1145/3220267.3220294.

[14] F. Z. El Idrysy, S. Hourri, I. El Miqdadi, A. Hayati, Y. Namir, B. Ncir and J. Kharroubi, Unlocking the language barrier: A journey through Arabic machine translation, Multimedia Tools and Applications 84(4) (2025), 14071 – 14104, DOI: 10.1007/s11042-024-19551-8.

[15] A. Farhat and A. Al-Taani, A rule-based English to Arabic machine translation approach, in: Proceedings of the The International Arab conference on information technology (ACIT’2015), (2015), 7 pages.

[16] D. Gamal, M. Alfonse, S. M. Jiménez-Zafra and M. Aref, Survey of Arabic machine translation, methodologies, progress, and challenges, in: 2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC, Cairo, Egypt, 2022), pp. 378 – 383, (2022), DOI: 10.1109/MIUCC55081.2022.9781776.

[17] I. Gashaw and H. L. Shashirekha, Amharic-Arabic neural machine translation, in: Proceedings of the 5th International Conference on Data Mining and Applications (DMAP2019, December 14, 2019), 15 pages.

[18] H. Hamed, A. M. Helmy and A. Mohammed, Deep learning approach for translating Arabic holy Quran into Italian language, in 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC, Cairo, Egypt, 2021), pp. 193 – 199 (2021), DOI: 10.1109/MIUCC52538.2021.9447650.

[19] I. T. Khemakhem, S. Jamoussi and A. B. Hamadou, Improving English-Arabic statistical machine translation with morpho-syntactic and semantic word class, International Journal of Intelligent Systems Technologies and Applications 19(2) (2020), 172 – 190, DOI: 10.1504/IJISTA.2020.107225.

[20] P. Koehn and R. Knowles, Six challenges for neural machine translation, in: Proceedings of the First Workshop on Neural Machine Translation, pp. 28 – 39, Vancouver, Association for Computational Linguistics, (2017), URL: https://aclanthology.org/W17-3204/.

[21] M.-T. Luong, H. Pham and C. D. Manning, Effective approaches to attention-based neural machine translation, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (Lisbon, Portugal, September 17-21, 2015), L. Màrquez, C. Callison-Burch and J. Su (editors), Association for Computational Linguistics, pp. 1412 – 1421, (2015), DOI: 10.18653/v1/D15-1166.

[22] D. Moussallem, M. Wauer and A.-C. N. Ngomo, Machine translation using semantic web technologies: A survey, Journal of Web Semantics 51 (2018), 1 – 19, DOI: 10.1016/j.websem.2018.07.001.

[23] Noor-e-Hira, S. A. Rauf, K. Kiani, A. Zafar and R. Nawaz, Exploring transfer learning and domain data selection for the biomedical translation, in: Proceedings of the Fourth Conference on Machine Translation (WMT, Vol. 3: Shared Task Papers (Day 2), Florence, Italy, August 1-2, 2019), Association for Computational Linguistics, pp. 156 – 163, (2019), DOI: 10.18653/v1/W19-5419.

[24] K. Papineni, S. Roukos, T. Ward and W.-J. Zhu, BLEU: A method for automatic evaluation of machine translation, in Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (Philadelphia, Pennsylvania, 2002), pp. 311 – 318 (2002), DOI: 10.3115/1073083.1073135.

[25] L. Qun and Z. Xiaojun, Machine translation: General, in: Routledge Encyclopedia of Translation Technology, 1st edition, C. Sin-Wai (editor), pp. 105–119, Routledge (2014).

[26] Y. Shalhoub-Awwad and M. Leikin, The lexical status of the root in processing morphologically complex words in Arabic, Scientific Studies of Reading 20(4) (2016), 296 – 310, DOI: 10.1080/10888438.2016.1180525.

[27] S. P. Singh, A. Kumar, H. Darbari, L. Singh, A. Rastogi and S. Jain, Machine translation using deep learning: An overview, in: 2017 international conference on computer, communications and electronics (Comptelix, Jaipur, India, 2017), pp. 162 – 167, (2017), DOI: 10.1109/COMPTELIX.2017.8003957.

[28] I. Sutskever, O. Vinyals and Q. V. Le, Sequence to sequence learning with neural networks, in: Proceedings of the 28th International Conference on Neural Information Processing Systems, Vol. 2 (Series NIPS’14, Cambridge, MA), MIT Press, USA, pp. 3104 – 3112, (2014).

[29] G. Thurmair, Comparing rule-based and statistical MT output, in: Proceedings of the Workshop on the Amazing Utility of Parallel and Comparable Corpora (Lisbon, Portugal, 2004), pp. 5 – 9, (2004), URL: https://aclanthology.org/www.mt-archive.info/LREC-2004-Thurmair-2.pdf.

[30] R. K. Yadav, S. Harwani, S. K. Maurya and S. Kumar, Intelligent chatbot using GNMT, SEQ-2-SEQ techniques, in: 2021 International Conference on Intelligent Technologies (CONIT, Hubli, India, 2021), pp. 1 – 5, (2021), DOI: 10.1109/CONIT51480.2021.9498485.

[31] J. Zakraoui, M. Saleh, S. Al-Maadeed and J. M. AlJa’am, Evaluation of Arabic to English machine translation systems, in: 2020 11th International Conference on Information and Communication Systems (ICICS, Irbid, Jordan, 2020), pp. 185 – 190, (2020), DOI: 10.1109/ICICS49469.2020.239518.