Article Sidebar

Tiếng Việt
Date Published: 28/02/2025
Abstract Views: 155
Views Tiếng Việt: 31
DOI: https://doi.org/10.54607/hcmue.js.22.2.4320(2025)
Issue
Vol. 22 No. 2 (2025)
Section
Articles
How to Cite
Le, C. T., Nguyen, P. N., Nguyen, H. B. L., & Tran, T. N. (2025). ENHANCING NEURAL MACHINE TRANSLATION WITH KNOWLEDGE GRAPH INTEGRATION. HCMUE Journal of Science, 22(2), 235-246. https://doi.org/10.54607/hcmue.js.22.2.4320(2025)

ENHANCING NEURAL MACHINE TRANSLATION WITH KNOWLEDGE GRAPH INTEGRATION

Cong Tri Le1, Phuong Nam Nguyen2, Hong Buu Long Nguyen3, Thanh Nha Tran1,
1 Trường Đại học Sư phạm Thành phố Hồ Chí Minh, Việt Nam
2 Trường Đại học Tài Nguyên và Môi trường thành phố Hồ Chí Minh, Việt Nam
3 Trường Đại học Khoa học Tự nhiên, Đại học Quốc gia Thành phố Hồ Chí Minh, Việt Nam

Main Article Content

Abstract

Machine translation is a critical issue in the field of natural language processing (NLP), aiming to produce translations from a source language to a target language with equivalent meaning. However, current neural machine translation (NMT) models struggle with handling entities, particularly in low-resource languages like Vietnamese. This paper proposes a method to enhance NMT models by integrating information from knowledge graphs (KGs) into the Transformer model. This method allows the model to learn the representations of entities during the training process, thereby improving automatic translation when encountering entities and similar linguistic elements. Experimental results show that the proposed method significantly improves the Transformer model’s translation quality, particularly in entity translation. These findings highlight the effectiveness of integrating knowledge graphs into NMT models and suggest new directions for research.

Keywords

BERT, natural language processing, machine translation, KG Integration, Knowledge Graph Embedding, Neural Machine Translation

Article Details

References

object detection with transformers. In European Conference on Computer Vision (pp.213-229). https://doi.org/10.1007/978-3-030-58452-8_13
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. North American Chapter of the Association for Computational Linguistics, 1, 4171-4186. https://doi.org/10.18653/v1/n19-1423
Du, J., Way, A., & Zydro’n, A. (2016). Using BabelNet to improve OOV coverage in SMT. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16) (pp.9-15).
Ehrlinger, L., & Wöß, W. (2016). Towards a definition of knowledge graphs. International Conference on Semantic Systems, 48, 1-4.
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017, July). Convolutional sequence to sequence learning. In International conference on machine learning (pp.1243-1252).
Guo, J., Zhang, Z., Xu, L., Chen, B., & Chen, E. (2021). Adaptive adapters: An efficient way to incorporate BERT into neural machine translation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1740-1751. https://doi.org/10.1109/TASLP.2021.3076863
Liu, W., Zhou, P., Zhao, Z., Wang, Z., Ju, Q., Deng, H., & Wang, P. (2020). K-BERT: Enabling language representation with knowledge graph. In 2021 International Conference on Computer Communication and Artificial Intelligence (CCAI), (pp.91-96). https://doi.org/10.1609/aaai.v34i03.5681
Lu, Y., Zhang, J., & Zong, C. (2018). Exploiting knowledge graph in neural machine translation. In China Workshop on Machine Translation (pp.27-38). https://doi.org/10.1007/978-981-13-3083-4_3
Melnyk, I., Dognin, P., & Das, P. (2022). Knowledge graph generation from text. Findings of the Association for Computational Linguistics: EMNLP 2022 (pp.1610-1622).
Moussallem, D., Ngonga Ngomo, A.-C., Buitelaar, P., & Arčan, M. (2019). Utilizing Knowledge Graphs for Neural Machine Translation Augmentation. In Proceedings of the 10th international conference on knowledge capture (pp.139-146). https://doi.org/10.1145/3360901.3364423
Navigli, R., & Ponzetto, S. P. (2010). BabelNet: Building a very large multilingual semantic network. Annual Meeting of the Association for Computational Linguistics (pp.216-225).
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). BLEU: A method for automatic evaluation of machine translation. Annual Meeting of the Association for Computational Linguistics (pp.311-318). https://doi.org/10.3115/1073083.1073135
Shi, C., Liu, S., Shi, C., Ren, S., Feng, S., Li, M., Zhou, M., & Sun, X. (2016). Knowledge-Based Semantic Embedding for Machine Translation. Annual Meeting of the Association for Computational Linguistics, 1, 2245-2254. https://doi.org/10.18653/v1/p16-1212
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Neural Information Processing Systems, 27, 3104-3112.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, 30. https://doi.org/10.48550/arXiv.1706.03762
Yao, S., Wang, R., Sun, S., Bu, D., & Liu, J. (2020). Joint embedding learning of educational knowledge graphs. In Artificial Intelligence Supported Educational Technologies. Advances in Analytics for Learning and Teaching (pp.1-12). Springer. https://doi.org/10.1007/978-3-030-41099-5_12
Wang, Z., Chen, T., Ren, J., Yu, W., Cheng, H., & Li, L. (2018). Deep reasoning with knowledge graph for social relationship understanding. International Joint Conference on Artificial Intelligence, 1021-1028. https://doi.org/10.24963/ijcai.2018/142