Integrating Hybrid AI Approaches for Enhanced Translation in Minority Languages
Source abstract
Abstract
This study presents a hybrid artificial intelligence model designed to enhance translation quality for low-resource languages, specifically targeting the Hakka language. The proposed model integrates phrase-based machine translation (PBMT) and neural machine translation (NMT) within a recursive learning framework. The methodology consists of three key stages: (1) initial translation using PBMT, where Hakka corpus data is structured into a parallel dataset; (2) NMT training with Transformers, leveraging the generated parallel corpus to train deep learning models; and (3) recursive translation refinement, where iterative translations further enhance model accuracy by expanding the training dataset. This study employs preprocessing techniques to clean and optimize the dataset, reducing noise and improving sentence segmentation. A BLEU score evaluation is conducted to compare the effectiveness of PBMT and NMT across various corpus sizes, demonstrating that while PBMT performs well with limited data, the Transformer-based NMT achieves superior results as training data increases. The findings highlight the advantages of a hybrid approach in overcoming data scarcity challenges for minority languages. This research contributes to machine translation methodologies by proposing a scalable framework for improving linguistic accessibility in under-resourced languages.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Natural Language Processing Techniques · Topic Modeling · Speech and dialogue systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Culture Creativity and Digital Marketing, College of Hakka Studies, National United University, Miaoli 36063, Taiwan
Department of Business and Management, College of Management and Design, Ming Chi University of Technology, New Taipei 243303, Taiwan
Department of Cultural Tourism, College of Hakka Studies, National United University, Miaoli 36063, Taiwan
Funding
National Science and Technology Council (NSTC), Taiwan · Ming Chi University of Technology
References (40)
Show source-provided references
1. Ethnic discrimination and bullying in the Sami and non-Sami populations in Norway: The SAMINOR study10.3402/ijch.v67i1.18243 ↗
2. The impact of the COVID-19 pandemic on marginalized populations in the United States: A research agenda10.1016/j.jvb.2020.103439 ↗
3. Linguistic diversity and social justice: An introduction of applied sociolinguistics10.1080/15427587.2018.1434930 ↗
4. Forcada, M. (2006, January 24–26). Open source machine translation: An opportunity for minor languages. Proceedings of the Workshop “Strategies for Developing Machine Translation for Minority Languages”, LREC, Genoa, Italy.
5. Technological disruption in foreign language teaching: The rise of simultaneous machine translation10.1017/S0261444818000253 ↗
6. Somers, H. (1997, January 13–14). Machine translation and minority languages. Proceedings of the Translating and the Computer 19, Manchester, UK.
7. Fair MT: Towards ethical, sustainable machine translation10.1075/ts.00018.int ↗
8. Sánchez-Cartagena, V.M., Forcada, M.L., and Sánchez-Martínez, F. (2020, January 3–5). A multi-source approach for Breton-French hybrid machine translation. Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, Lisboa, Portugal.
9. Ambati, V., and Carbonell, J.G. (2009, January 5). Proactive learning for building machine translation systems for minority languages. Proceedings of the NAACL HLT 2009 Workshop on Active Learning for Natural Language Processing, Boulder, CO, USA.10.3115/1564131.1564143 ↗
10. Costa-jussà, M.R., Cross, J., Çelebi, O., Elbayad, M., Heafield, K., Heffernan, K., Kalbassi, E., Lam, J., Licht, D., and Maillard, J. (2022). No language left behind: Scaling human-centered machine translation. arXiv.
11. Altered states: Translation and minority languages
12. Introduction: Multiple roles of translation in the context of minority languages and revitalisation
13. Orynycz, P. (2023). BLEU Skies for Endangered Language Revitalization: Lemko Rusyn and Ukrainian Neural AI Translation Accuracy Soars. International Conference on Human-Computer Interaction, Springer.10.1007/978-3-031-35894-4_10 ↗
14. Herbig, N., Pal, S., van Genabith, J., and Krüger, A. (2019). Integrating Artificial and Human Intelligence for Efficient Translation. arXiv.
15. Survey of Low-Resource Machine Translation10.1162/coli_a_00446 ↗
16. Hung, Y.-H., and Huang, Y.-C. (2022, January 21–22). A Preliminary Study on Mandarin-Hakka neural machine translation using small-sized data. Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022), Taipei, Taiwan.
17. Neural machine translation for low-resource languages without parallel corpora10.1007/s10590-017-9203-5 ↗
18. Advances in machine translation systems
19. Awadalla, H.H. (2025, August 13). Bringing Low-Resource Languages and Spoken Dialects into Play with Semi-Supervised Universal Neural Machine Translation. Microsoft Research Blog. Available online: https://www.microsoft.com/en-us/research/blog/bringing-low-resource-languages-spoken-dialects-play-semi-supervised-universal-neural-machine-translation/.
20. Artificial neural network: Understanding the basic concepts without mathematics10.12779/dnd.2018.17.3.83 ↗
21. Toward a theory of machine learning10.1088/2632-2153/abe6d7 ↗
22. Neural networks for machine learning applications10.30574/wjarr.2020.6.1.0055 ↗
23. Bahdanau, D. (2014). Neural machine translation by jointly learning to align and translate. arXiv.
24. Bisong, E., and Bisong, E. (2019). Recurrent Neural Networks (RNNs). Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners, Apress.10.1007/978-1-4842-4470-8 ↗
25. Lipton, Z.C. (2015). A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv.
26. Understanding recurrent neural network for texts using English-Korean corpora
27. Agrawal, R., and Sharma, D.M. (, 2017). Experiments on different recurrent neural networks for English-Hindi machine translation. Proceedings of the Computer Science and Information Technology (CS & IT), Telangana, India.10.5121/csit.2017.71006 ↗
28. Neural Machine Translation (NMT): Deep learning approaches through Neural Network Models10.54254/2755-2721/82/20240944 ↗
29. Cho, K. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv.10.3115/v1/W14-4012 ↗
30. Karita, S., Chen, N., Hayashi, T., Hori, T., Inaguma, H., Jiang, Z., Someki, M., Soplin, N.E.Y., Yamamoto, R., and Wang, X. (2019, January 14–18). A comparative study on transformer vs rnn in speech applications. Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Singapore.10.1109/ASRU46091.2019.9003750 ↗
31. Raganato, A., and Tiedemann, J. (2018, January 1). An analysis of encoder representations in transformer-based machine translation. Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, Brussels, Belgium. The Association for Computational Linguistics.10.18653/v1/W18-5431 ↗
32. Application of data storage and information search in english translation corpus
33. Harrat, S., Meftouh, K., and Smaïli, K. (2017, January 17–23). Creating parallel Arabic dialect corpus: Pitfalls to avoid. Proceedings of the 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLING), Budapest, Hungary.
34. Issues of culture specific item translation in subtitling10.1016/j.sbspro.2016.09.095 ↗
35. Hasan, T., Bhattacharjee, A., Samin, K., Hasan, M., Basak, M., Rahman, M.S., and Shahriyar, R. (2020, January 16–20). Not low-resource anymore: Aligner ensembling, batch filtering, and new datasets for Bengali-English machine translation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium. Online: Association for Computational Linguistics.10.18653/v1/2020.emnlp-main.207 ↗
36. Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002, January 7–12). Bleu: A method for automatic evaluation of machine translation. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA.10.3115/1073083.1073135 ↗
37. The METEOR metric for automatic evaluation of machine translation10.1007/s10590-009-9059-4 ↗
38. Ter-plus: Paraphrase, semantic, and alignment enhancements to translation edit rate10.1007/s10590-009-9062-9 ↗
39. Gibadullin, I., Valeev, A., Khusainova, A., and Khan, A. (2019). A survey of methods to leverage monolingual data in low-resource neural machine translation. arXiv.
40. The dynamics of language minorities: Evidence from an agent-based model of language contact10.18564/jasss.4097 ↗