Abstract
One of the major tasks in producer-customer relations is a processing of customers’ feedback. Since for the international companies provide their products for a lot of countries the feedback could be provided with various languages. That can produce a number of difficulties during automatic text processing. One of the solutions is to use one common language to process feedback and automatically translate feedbacks from the various languages to the common one. Then the translated feedback could be processed with the configured pipeline. This paper compares existing open models for automatic text translation. Only language models with Transformer architecture were considered due to the best results of translation over other existing approaches. The models are: M2M100, mBART, OPUS-MT (Helsinki NLP). Own test data was built due to requirement of translation for texts specific to the subject area. To create dataset Microsoft Azure Translation was chosen as the reference translation with manual translation verification for grammar. Translations produced by each model were compared with the reference translation using two metrics: BLEU and METEOR. The possibility of fast fine-tuning of models was also investigated to improve the quality of address the translation on specific lexicon of the problem area. Among the reviewed models, M2M100 turned out to be the best in terms of translation quality, but it is also the most difficult to fine-tune it.
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
References
Usuga Cadavid, J.P., Lamouri, S., Grabot, B., Pellerin, R., Fortin, A.: Machine learning applied in production planning and control: a state-of-the-art in the era of industry 4.0. J. Intell. Manuf. 31(6), 1531–1558 (2020). https://doi.org/10.1007/s10845-019-01531-7
Cioffi, R., Travaglioni, M., Piscitelli, G., Petrillo, A., De Felice, F.: Artificial intelligence and machine learning applications in smart production: progress, trends, and directions. Sustainability 12, 492 (2020). https://doi.org/10.3390/su12020492
Zhang, J., Zong, C.: Neural machine translation: challenges, progress and future. Sci. China Technol. Sci. 63(10), 2028–2050 (2020). https://doi.org/10.1007/s11431-020-1632-x
Jooste, W., Haque, R., Way, A., Koehn, P.: Neural machine translation. Mach. Transl. 35, 289–299 (2021). https://doi.org/10.1007/s10590-021-09277-x
Stahlberg, F.: Neural machine translation: a review. J. Artif. Intell. Res. 69, 343–418 (2020). https://doi.org/10.1613/jair.1.12007
Google: Google Tranlate. https://translate.google.com/. Accessed 2022/01/12
Microsoft: Microsoft Bing Translator. https://www.bing.com/translator. Accessed 12 Jan 2022
Smirnov, A., Teslya, N., Shilov, A., Frank, D., Minina, E., Kovacs, M.: Comparative analysis of neural translation models based on transformers architecture. In: Proceedings of the 24th International Conference on Enterprise Information Systems, pp. 586–593. SCITEPRESS - Science and Technology Publications (2022). https://doi.org/10.5220/0011083600003179
Vathsala, M.K., Holi, G.: RNN based machine translation and transliteration for Twitter data. Int. J. Speech Technol. 23, 499–504 (2020). https://doi.org/10.1007/s10772-020-09724-9
Mahata, S.K., Das, D., Bandyopadhyay, S.: MTIL2017: machine translation using recurrent neural network on statistical machine translation. J. Intell. Syst. 28, 447–453 (2019). https://doi.org/10.1515/jisys-2018-0016
Wang, X., Chen, C., Xing, Z.: Domain-specific machine translation with recurrent neural network for software localization. Empir. Softw. Eng. 24, 3514–3545 (2019). https://doi.org/10.1007/s10664-019-09702-z
Wolf, T., et al.: Hugging face’s transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pp. 38–45. Association for Computational Linguistics, Stroudsburg, PA, USA (2020). https://doi.org/10.18653/v1/2020.emnlp-demos.6
Wolf, T., et al.: Hugging Face’s Transformers: State-of-the-art Natural Language Processing. arXiv Prepr. arXiv1910.03771 (2019)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018)
Fan, A., et al.: Beyond English-centric multilingual machine translation. J. Mach. Learn. Res. 22, 1–48 (2021)
Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726–742 (2020). https://doi.org/10.1162/tacl_a_00343
Tiedemann, J., Thottingal, S.: OPUS-MT: building open translation services for the world. In: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pp. 479–480 (2020)
Tan, Z., et al.: Neural machine translation: a review of methods, resources, and tools. AI Open 1, 5–21 (2020). https://doi.org/10.1016/j.aiopen.2020.11.001
Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 311–318. Philadelphia (2002)
Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376–380. Association for Computational Linguistics, Stroudsburg, PA, USA (2014). https://doi.org/10.3115/v1/W14-3348
Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In: HLT ’02: Proceedings of the second international conference on Human Language Technology Research, pp. 138–145. ACM Press (2002). https://doi.org/10.5555/1289189.1289273
Chen, B., et al.: Transformer-based language model fine-tuning methods for COVID-19 fake news detection. In: Chakraborty, T., Shu, K., Bernard, H.R., Liu, H., Akhtar, M.S. (eds.) CONSTRAINT 2021. CCIS, vol. 1402, pp. 83–92. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-73696-5_9
Mishra, S., Prasad, S., Mishra, S.: Multilingual joint fine-tuning of transformer models for identifying trolling, aggression and cyberbullying at TRAC 2020. In: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying at Language Resources and Evaluation Conference (LREC 2020), pp. 120–125. European Language Resources Association (ELRA) (2020)
Acknowledgements
The paper is due to the collaboration between SPC RAS and Festo SE & Co. KG. The methodology and experiment setup (Sect. 3) are partially due to the State Research, project number FFZF-2022-0005.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Smirnov, A., Teslya, N., Shilov, N., Frank, D., Minina, E., Kovacs, M. (2023). Quantitative Comparison of Translation by Transformers-Based Neural Network Models. In: Filipe, J., Śmiałek, M., Brodsky, A., Hammoudi, S. (eds) Enterprise Information Systems. ICEIS 2022. Lecture Notes in Business Information Processing, vol 487. Springer, Cham. https://doi.org/10.1007/978-3-031-39386-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-39386-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39385-3
Online ISBN: 978-3-031-39386-0
eBook Packages: Computer ScienceComputer Science (R0)