Abstract
Neural Machine Translation (NMT) systems have been shown to perform impressively on many language pairs compared to Statistical Machine Translation (SMT). However, these systems are data-intensive, which is problematic for the majority of language pairs, and especially for low-resource languages. In this work, we address this issue in the case of certain Arabic dialects, those variants of Modern Standard Arabic (MSA) that are spelling non-standard, morphologically rich, and yet resource-poor variants. Here, we have experimented with several multitasking learning strategies to take advantage of the relationships between these dialects. Despite the simplicity of this idea, empirical results show that several multitasking learning strategies are capable of achieving remarkable performance compared to statistical machine translation. For instance, we obtained the BLUE scores for the Algerian \(\rightarrow \) Modern-Standard-Arabic and the Moroccan \(\rightarrow \) Palestinian of 35.06 and 27.55, respectively, while the scores obtained with a statistical method are 15.1 and 18.91 respectively. We show that on 42 machine translation experiments, and despite the use of a small corpus, multitasking learning achieves better performance than statistical machine translation in 88% of cases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Baniata, L.H., Park, S., Park, S.B.: A multitask-based neural machine translation model with part-of-speech tags integration for Arabic dialects. Appl. Sci. 8(12), 2502 (2018)
Baniata, L.H., Park, S., Park, S.B.: A neural machine translation model for Arabic dialects that utilizes multitask learning (MTL). Comput. Intell. Neurosci. (2018)
Boudlal, A., Lakhouaja, A., Mazroui, A., Meziane, A., Bebah, M., Shoul, M.: Alkhalil morpho Sys1: a morphosyntactic analysis system for Arabic texts. In: International Arab Conference on Information Technology, pp. 1–6. Elsevier Science, NY (2010)
Chiang, D., Diab, M., Habash, N., Rambow, O., Shareef, S.: Parsing Arabic dialects. In: 11th Conference of the European Chapter of the Association for Computational Linguistics (2006)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160–167 (2008)
Deng, L., Hinton, G., Kingsbury, B.: New types of deep neural network learning for speech recognition and related applications: an overview. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8599–8603. IEEE (2013)
Durrani, N., Koehn, P.: Improving machine translation via triangulation and transliteration. In: Proceedings of the 17th Annual Conference of the European Association for Machine Translation, pp. 71–78 (2014)
Erdmann, A., Habash, N., Taji, D., Bouamor, H.: Low resourced machine translation via morpho-syntactic modeling: the case of dialectal Arabic. arXiv preprint arXiv:1712.06273 (2017)
Ferguson, C.A.: Diglossia. Word 15(2), 325–340 (1959)
Hamdi, A., Boujelbane, R., Habash, N., Nasr, A.: The effects of factorizing root and pattern mapping in bidirectional Tunisian-standard Arabic machine translation (2013)
Harrat, S., Meftouh, K., Abbas, M., Smaïli, K.: Grapheme to phoneme conversion - an Arabic dialect case. In: Spoken Language Technologies for Under-Resourced Languages. Saint Petesbourg, Russia (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Long, M., Wang, J.: Learning multiple tasks with deep relationship networks. arXiv preprint arXiv:1506.02117 (2015)
Meftouh, K., Harrat, S., Smaïli, K.: PADIC: extension and new experiments. In: 7th International Conference on Advanced Technologies ICAT. Antalya, Turkey (2018)
Meftouh, K., Bouchemal, N., Smaïli, K.: A study of a non-resourced language: the case of one of the Algerian dialects. In: The Third International Workshop on Spoken Languages Technologies for Under-Resourced Languages-SLTU 2012, pp. 1–7 (2012)
Meftouh, K., Harrat, S., Jamoussi, S., Abbas, M., Smaili, K.: Machine translation experiments on PADIC: a parallel Arabic dialect corpus. In: The 29th Pacific Asia Conference on Language, Information And Computation (2015)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026–8037 (2019)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Tachicart, R., Bouzoubaa, K.: A hybrid approach to translate Moroccan Arabic dialect. In: 2014 9th International Conference on Intelligent Systems: Theories and Applications (SITA 2014), pp. 1–5. IEEE (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Moukafih, Y., Sbihi, N., Ghogho, M., Smaili, K. (2022). Improving Machine Translation of Arabic Dialects Through Multi-task Learning. In: Bandini, S., Gasparini, F., Mascardi, V., Palmonari, M., Vizzari, G. (eds) AIxIA 2021 – Advances in Artificial Intelligence. AIxIA 2021. Lecture Notes in Computer Science(), vol 13196. Springer, Cham. https://doi.org/10.1007/978-3-031-08421-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-08421-8_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08420-1
Online ISBN: 978-3-031-08421-8
eBook Packages: Computer ScienceComputer Science (R0)