Low-Resourced Alphabet-Level Pivot-Based Neural Machine Translation for Translating Korean Dialects
Source abstract
Abstract
Developing a machine translator from a Korean dialect to a foreign language presents significant challenges due to a lack of a parallel corpus for direct dialect translation. To solve this issue, this paper proposes a pivot-based machine translation model that consists of two sub-translators. The first sub-translator is a sequence-to-sequence model with minGRU as an encoder and GRU as a decoder. It normalizes a dialect sentence into a standard sentence, and it employs alphabet-level tokenization. The other type of sub-translator is a legacy translator, such as off-the-shelf neural machine translators or LLMs, which translates the normalized standard sentence to a foreign sentence. The effectiveness of the alphabet-level tokenization and the minGRU encoder for the normalization model is demonstrated through empirical analysis. Alphabet-level tokenization is proven to be more effective for Korean dialect normalization than other widely used sub-word tokenizations. The minGRU encoder exhibits comparable performance to GRU as an encoder, and it is faster and more effective in managing longer token sequences. The pivot-based translation method is also validated through a broad range of experiments, and its effectiveness in translating Korean dialects to English, Chinese, and Japanese is demonstrated empirically.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Natural Language Processing Techniques · Topic Modeling · Speech Recognition and Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computing, Kyung-Hee University, Giheung-gu, Yongin-si 17104, Gyeonggi-do, Republic of Korea
Funding
Institute of Information & Communications Technology Planning & Evaluation (IITP)-ITRC (Information Technology Research Center) · Institute of Information & communications Technology Planning & Evaluation (IITP)
References (38)
Show source-provided references
1. Choi, M.O. (1995). Korean Dialects, Sechang.
2. Li, J., Shen, Y., Huang, S., Dai, X., and Chen, J. (2021, January 1–6). When is char better than subword: A systematic study of segmentation algorithms for neural machine translation. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online.10.18653/v1/2021.acl-short.69 ↗
3. Chen, Y., Liu, Y., Cheng, Y., and Li, V. (August, January 30). A Teacher-Student Framework for Zero-Resource Neural Machine Translation. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, BC, Canada.
4. Firat, O., Sankaran, B., Al-Onaizan, Y., Vural, F., and Cho, K.H. (2016, January 1–5). Zero-Resource Translation with Multi-lingual Neural Machine Translation. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.10.18653/v1/D16-1026 ↗
5. Kim, Y.S., Petrov, P., Petrushkov, P., and Ney, H. (2019, January 3–7). Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Hong Kong, China.10.18653/v1/D19-1080 ↗
6. Kuparinen, O., Miletić, A., and Scherrer, Y. (2023, January 6–10). Dialect-to-Standard Normalization: A Large-Scale Multilingual Evaluation. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.10.18653/v1/2023.findings-emnlp.923 ↗
7. Tan, S., Joty, S., Varshney, L., and Kan, M.Y. (2020, January 16–20). Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Online.10.18653/v1/2020.emnlp-main.455 ↗
8. Abe, K., Matsubayashi, Y., Okazaki, N., and Inui, K. (2018, January 1–3). Multi-dialect Neural Machine Translation and Dialectometry. Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation, Hong Kong, China.
9. Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation10.1162/tacl_a_00065 ↗
10. Honnet, P.E., Popescu-Belis, A., Musat, C., and Baeriswyl, M. (2018, January 7–12). Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German. Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan.
11. Sajjad, H., Darwish, K., and Belinkov, Y. (2013, January 4–9). Translating Dialectual Arabic to English. Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria.
12. Faheem, M., Wassif, K., Bayomi, H., and Abdou, S. (2024). Improving neural machine translation for low resource languages through non-parallel corpora: A case study of Egyptian dialect to modern standard Arabic translation. Sci. Rep., 14.10.1038/s41598-023-51090-4 ↗
13. Liu, Z., Ni, S., Aw, A., and Chen, N. (2022, January 12–17). Singlish Message Paraphrasing: A Joint Task of Creole Translation and Text Normalization. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea.
14. Paul, M., Finch, A., Dixon, P., and Sumita, E. (2011, January 31). Dialect Translation: Integrating Bayesian Co-segmentation Models with Pivot-based SMT. Proceedings of the 1st Workshop on Algorithms and Resources for Modelling of Dialects and Language Varieties, Edinburgh, UK.
15. Jeblee, S., Feely, W., Bouamor, H., Lavie, A., Habash, N., and Oflazer, K. (2014, January 25–29). Domain and Dialect Adaptation for Machine Translation into Egyptian Arabic. Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing, Doha, Qatar.10.3115/v1/W14-3627 ↗
16. Edunov, S., Ott, M., Auli, M., and Grangier, D. (November, January 31). Understanding Back-Translation at Scale. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1045 ↗
17. Sennrich, R., Haddow, B., and Birch, A. (2016, January 7–12). Improving Neural Machine Translation Models with Monolingual Data. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.10.18653/v1/P16-1009 ↗
18. Tahssin, R., Kishk, Y., and Torki, M. (2020, January 12). Identifying Nuanced Dialect for Arabic Tweets with Deep Learning and Reverse Translation Corpus Extension System. Proceedings of the 5th Arabic Natural Language Processing Workshop, Barcelona, Spain.
19. FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation10.1162/tacl_a_00568 ↗
20. Sun, J., Sellam, T., Clark, E., Vu, T., Dozat, T., Garrette, D., Siddhant, A., Eisenstein, J., and Gehrmann, S. (2023, January 9–14). Dialect-robust Evaluation of Generated Text. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, ON, Canada.10.18653/v1/2023.acl-long.331 ↗
21. Deep Learning-based Korean Machine Translation Research Considering Linguistics Features and Service
22. Hwang, J.S., and Yang, H.C. (February, January 31). Korean dialect-standard language translation using special token in KoBART. Proceedings of the Symposium of the Korean Institute of Communications and Information Sciences, Pyeongchang, Republic of Korea.
23. Lee, S.Y., Jung, D.-E., Sim, J.Y., and Kim, S.H. (2024, January 26–28). Study on Jeju Dialect Machine Translation Utilizing an Open-Source Large Language Model. Proceedings of the Summer Annual Conference of IEIE 2024, Jeju, Republic of Korea.
24. A Basic Performance Evaluation of the Speech Recognition APP of Standard Language and Dialect using Google, Naver, and Daum KAKAO APIs
25. Na, J., Park, Y., and Lee, B. (2024, January 3–6). A Comparative Study on the Biases of Age, Gender, Dialects, and L2 speakers of Automatic Speech Recognition for Korean Language. Proceedings of the 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Macau, China.10.1109/APSIPAASC63619.2025.10848815 ↗
26. Bak, S.H., Choi, S.M., and Jung, Y.C. (2025, January 14–17). Voice Recognition Control using LLM for Regional Dialects. Proceedings of the KIIT Conference, Jeju, Republic of Korea.
27. An, S.Y., Bae, K.H., Choi, E.B., Choi, S., Choi, Y.M., Hong, S.K., Hong, Y.J., Hwang, J.W., Jeon, H.J., and Jo, G. (2024). EXAONE 3.0 7.8B Instruction Tuned Language Model. arXiv.
28. Cho, K.H., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25–29). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar.10.3115/v1/D14-1179 ↗
29. Feng, L., Tung, F., Ahmed, M., Bengio, Y., and Hajimirsadeghi, H. (2024). Were RNNs All We Needed?. arXiv.
30. Blelloch, G. (1990). Prefix Sums and Their Applications, School of Computer Science, Carnegie Mellon University. Technical Report CMU-CS-90-190.
31. Heinsen, F. (2023). Efficient Parallelization of a Ubiquitous Sequential Computation. arXiv.
32. Luong, T., Pham, H., Manning, C., and Su, J. (2015, January 17–21). Effective Approaches to Attention-based Neural Machine Translation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.10.18653/v1/D15-1166 ↗
33. Tiedemann, J., and Thottingal, S. (2020, January 3–5). OPUS-MT—Building open translation services for the World. Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, Lisboa, Portugal.
34. Beyond English-Centric Multilingual Machine Translation
35. Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H., Heafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A., and Bogoychev, N. (2018, January 15–20). Marian: Fast Neural Machine Translation in C++. Proceedings of the ACL 2018, System Demonstrations, Melbourne, Australia.10.18653/v1/P18-4020 ↗
36. Tiedemann, J. (2012, January 23–25). Parallel Data, Tools and Interfaces in OPUS. Proceedings of the 8th International Conference on Language Resources and Evaluation, Istanbul, Turkey.
37. Sim, Y.J., Lee, W.J., Kim, H.J., and Kim, H.S. (2024, January 11–12). Evaluating Large Language Models on Korean Cultural Understanding in Empathetic Response Generation. Proceedings of the 36th Annual Conference on Human and Cognitive Language Technology, Seongnam, Republic of Korea.
38. Barrault, L., Bojar, O., Bougares, F., Chatterjee, R., Costa-jussa, M.R., Federmann, C., Fishel, M., Fraser, A., Freitag, M., and Graham, Y. (2021, January 10–11). A Fine-Grained Analysis of BERTScore. Proceedings of the Sixth Conference on Machine Translation, Online.