Skip to main content

Neural Machine Translation of Low Resource Languages: Application to Transcriptions of Tunisian Dialect

  • Conference paper
  • First Online:
Intelligent Systems and Pattern Recognition (ISPR 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1589))

  • 621 Accesses

Abstract

With the evolution of speech technologies, the need to understand and process the poorly spoken language has gradually become a necessity. However, the lack of resources is the main computational processing challenge. We present, in this paper, an effort to create a Neural Machine Translation (NMT) model in order to translate the spoken language in Tunisia: The Tunisian Dialect (TD) into the Arabic Standard Language (MSA). Indeed, NMT tasks require an enormous amount of training data which represents a problematic for low resourced languages like TD. For this, two contributions will be presented in this paper, the first consists of the creating of a parallel corpus TD-MSA. Then, by exploiting the resulting corpus, we proposed a configuration of a neural translation model that achieved a BLEU score of 67.56%.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://www.researchgate.net/figure/presents-some-statistics-of-the-TARIC-corpus_tbl1_342420693.

  2. 2.

    https://www.researchgate.net/figure/Some-annotations-used-in-STAC-corpus_tbl2_307583782.

  3. 3.

    https://github.com/sk-cmd/PARallel-Speech-Corpus-of-tunisian-Arabic-Dialect/tree/main.

References

  1. Al-Ibrahim, R., Duwairi, R.M.: Neural machine translation from Jordanian dialect to modern standard Arabic. In: 2020 11th International Conference on Information and Communication Systems (ICICS), pp. 173–178 (2020). https://doi.org/10.1109/ICICS49469.2020.239505

  2. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2016)

    Google Scholar 

  3. 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, 10 (2018)

    Article  Google Scholar 

  4. Bouamor, H., et al.: The MADAR Arabic dialect corpus and lexicon. In: Proceedings of the 11th Language Resources and Evaluation Conference. Miyazaki, Japan (2018)

    Google Scholar 

  5. Boujelbane, R., Khemekhem, M.E, Belguith, L.H.: Mapping rules for building a Tunisian dialect lexicon and generating corpora. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 419–428. Asian Federation of Natural Language Processing, Nagoya, Japan (2013). https://www.aclweb.org/anthology/I13-1048

  6. Boukadida, N.: Connaissances phonologiques et morphologiques dérivationnelles et apprentissage de la lecture en arabe (etude longitudinale) (2008)

    Google Scholar 

  7. Cho, K., van Merriënboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103–111. Association for Computational Linguistics, Doha, Qatar (2014). https://doi.org/10.3115/v1/W14-4012. https://aclanthology.org/W14-4012

  8. Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neural machine translation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 567–573. Association for Computational Linguistics, Vancouver, Canada (2017). https://doi.org/10.18653/v1/P17-2090. https://aclanthology.org/P17-2090

  9. Folajimi, Y., Isaac, O.: Using statistical machine translation (SMT) as a language translation tool for understanding Yoruba language (2012). https://doi.org/10.13140/2.1.3522.8485

  10. Hamdi, A., Boujelbane, R., Habash, N., Nasr, A.: The effects of factorizing root and pattern mapping in bidirectional Tunisian - standard Arabic machine translation. In: MT Summit 2013. p. pas d’édition papier. France (2013). https://hal.archives-ouvertes.fr/hal-00908761

  11. Kchaou, S., Boujelbane, R., Hadrich-Belguith, L.: Parallel resources for Tunisian Arabic dialect translation. In: Proceedings of the Fifth Arabic Natural Language Processing Workshop, pp. 200–206. Association for Computational Linguistics, Barcelona, Spain (2020). https://www.aclweb.org/anthology/2020.wanlp-1.18

  12. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)

    Google Scholar 

  13. Masmoudi, A., Khmekhem, M.E., Estève, Y., Belguith, L.H., Habash, N.: A corpus and phonetic dictionary for Tunisian Arabic speech recognition. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC2014), pp. 306–310. European Language Resources Association (ELRA), Reykjavik, Iceland (2014). http://www.lrec-conf.org/proceedings/lrec2014/pdf/454_Paper.pdf

  14. Nagy, A., Nanys, P., Konrád, B.F., Bial, B., Ács, J.: Syntax-based data augmentation for Hungarian-English machine translation (2022)

    Google Scholar 

  15. Przystupa, M., Abdul-Mageed, M.: Neural machine translation of low-resource and similar languages with backtranslation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pp. 224–235. Association for Computational Linguistics, Florence, Italy (2019). https://doi.org/10.18653/v1/W19-5431. https://aclanthology.org/W19-5431

  16. Richburg, A., Eskander, R., Muresan, S., Carpuat, M.: An evaluation of subword segmentation strategies for neural machine translation of morphologically rich languages. In: Proceedings of the The Fourth Widening Natural Language Processing Workshop, pp. 151–155. Association for Computational Linguistics, Seattle, USA (2020). https://doi.org/10.18653/v1/2020.winlp-1.40. https://www.aclweb.org/anthology/2020.winlp-1.40

  17. Takezawa, T., Genichiro, K., Masahide, M., Eiichiro, S.: Multilingual spoken language corpus development for communication research. In: Chinese Spoken Language Processing, pp. 781–791 (2006)

    Google Scholar 

  18. Tapo, A.A., et al.: Neural machine translation for extremely low-resource African languages: a case study on Bambara. In: Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages, pp. 23–32. Association for Computational Linguistics, Suzhou, China (2020). https://aclanthology.org/2020.loresmt-1.3

  19. Vu, V.H., Nguyen, P., Nguyen, H., Shin, J.C., Ock, C.Y.: Korean-vietnamese neural machine translation with named entity recognition and part-of-speech tags. IEICE Trans. Inf. Syst. E103.D, 866–873 (2020). https://doi.org/10.1587/transinf.2019EDP7154

    Article  Google Scholar 

  20. Zribi, I., Boujelbane, R., Masmoudi, A., Ellouze, M., Belguith, L., Habash, N.: A conventional orthography for Tunisian Arabic. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC2014), pp. 2355–2361. European Language Resources Association (ELRA), Reykjavik, Iceland (2014). http://www.lrec-conf.org/proceedings/lrec2014/pdf/219_Paper.pdf

  21. Zribi, I., Kammoun, I., Ellouze, M., Hadrich Belguith, L., Blache, P.: Sentence boundary detection for transcribed Tunisian Arabic. In: Konvens-2016. RUHR-UNIVERSITAT BOCHUM, Bochum, Germany (2016), https://hal.archives-ouvertes.fr/hal-01462133

  22. Zribi, I., Ellouze, M., Belguith, L., Blache, P.: Spoken Tunisian Arabic corpus “stac’’: transcription and annotation. Res. Comput. Sci. 90, 123–135 (2015). https://doi.org/10.13053/rcs-90-1-9

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Abida Emna .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Emna, A., Kchaou, S., Boujelban, R. (2022). Neural Machine Translation of Low Resource Languages: Application to Transcriptions of Tunisian Dialect. In: Bennour, A., Ensari, T., Kessentini, Y., Eom, S. (eds) Intelligent Systems and Pattern Recognition. ISPR 2022. Communications in Computer and Information Science, vol 1589. Springer, Cham. https://doi.org/10.1007/978-3-031-08277-1_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-08277-1_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-08276-4

  • Online ISBN: 978-3-031-08277-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics