Semantic Role Labeling in Neural Machine Translation Addressing Polysemy and Ambiguity Challenges
DOI:
https://doi.org/10.51903/jtie.v4i1.274Keywords:
Neural Machine Translation (NMT), Semantic Role Labeling (SRL), Translation AccuracyAbstract
The persistent challenges of polysemy and ambiguity continue to hinder the semantic accuracy of Neural Machine Translation (NMT), particularly in language pairs with distinct syntactic structures. While transformer-based models such as BERT and GPT have achieved notable progress in capturing contextual word meanings, they still fall short in understanding explicit semantic roles. This study aims to address this limitation by integrating Semantic Role Labeling (SRL) into a Transformer-based NMT framework to enhance semantic comprehension and reduce translation errors. Using a parallel corpus of 100,000 English-Indonesian and English-Japanese sentence pairs, the proposed SRL-enhanced NMT model was trained and evaluated against a baseline Transformer NMT. The integration of SRL enabled the model to annotate semantic roles, such as agent, patient, and instrument, which were fused with encoder representations through semantic-aware attention mechanisms. Experimental results demonstrate that the SRL-integrated model significantly outperformed the standard NMT model, improving BLEU scores by 6.2 points (from 32.5 to 38.7), METEOR scores by 6.3 points (from 58.5 to 64.8), and reducing the TER by 5.8 points (from 45.1 to 39.3). These results were statistically validated using a paired t-test (p < 0.05). Furthermore, qualitative analyses confirmed SRL's effectiveness in resolving lexical ambiguities and syntactic uncertainties. Although SRL integration increased inference time by 12%, the performance trade-off was deemed acceptable for applications requiring higher semantic fidelity. The novelty of this research lies in the architectural fusion of SRL with transformer-based attention layers in NMT, a domain seldom explored in prior studies. Moreover, the model demonstrates robust performance across linguistically divergent language pairs, suggesting its broader applicability. This work contributes to the advancement of semantically aware translation systems and paves the way for future research in unsupervised SRL integration and multilingual scalability.
References
Anand, A., Jairath, A., Lal, N., Bangar, S., Sikka, J., Verma, A., Shah, R. R., & Satoh, S. (2023). GEC-DCL: Grammatical Error Correction Model with Dynamic Context Learning for Paragraphs and Scholarly Papers. International Conference on Big Data Analytics, 14418, 95–110. https://doi.org/10.1007/978-3-031-49601-1_7
Ariyanto, A. D. P., Fatichah, C., & Purwitasari, D. (2023). Semantic Role Labeling for Information Extraction on Indonesian Texts: A Literature Review. International Seminar on Intelligent Technology and Its Applications, 119–124. https://doi.org/10.1109/isitia59021.2023.10221008
Chang, W. L., & Sun, J. C. Y. (2024). Evaluating AI’s Impact on Self-Regulated Language Learning: A Systematic Review. System, 126, 103484. https://doi.org/10.1016/j.system.2024.103484
Cheng, N., Yan, Z., Wang, Z., Li, Z., Yu, J., Zheng, Z., Tu, K., Xu, J., & Han, W. (2024). Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL. International Conference on Intelligent Computing, 14875, 50–61. https://doi.org/10.1007/978-981-97-5663-6_5
Cohen, F. S., Zhong, Z., & Li, C. (2022). Semantic Graph for Word Disambiguation in Machine Translation. Multimedia Tools and Applications, 81(30), 43485–43502. https://doi.org/10.1007/s11042-022-13242-y
Devi, M. I., & Purkayastha, B. S. (2023). An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation. Lecture Notes in Networks and Systems, 720, 329–338. https://doi.org/10.1007/978-981-99-3761-5_31
Do Campo Bayón, M., & Sánchez-Gijón, P. (2024). Evaluating NMT Using the Non-Inferiority Principle. Natural Language Processing, 1–20. https://doi.org/10.1017/nlp.2024.4
Habtamu, R., & Gizachew, B. (2024). State-of-the-Art Approaches to Word Sense Disambiguation: A Multilingual Investigation. Communications in Computer and Information Science, 2068, 176–202. https://doi.org/10.1007/978-3-031-57624-9_10
Harsha, N. S., Kumar, C. N., Sonthi, V. K., & Amarendra, K. (2022). Lexical Ambiguity in Natural Language Processing Applications. International Conference on Electronics and Renewable Systems, 1550–1555. https://doi.org/10.1109/icears53579.2022.9752297
Huang, Y., & Xin, Y. (2022). Deep Learning-Based English-Chinese Translation Research. Advances in Meteorology, 2022(1), 3208167. https://doi.org/10.1155/2022/3208167
Jooste, W., Haque, R., & Way, A. (2022). Knowledge Distillation: A Method for Making Neural Machine Translation More Efficient. Information, 13(2), 88. https://doi.org/10.3390/info13020088
Kijania-Placek, K. (2023). The Polysemy of Proper Names. Philosophical Studies, 180(10–11), 2897–2935. https://doi.org/10.1007/s11098-023-02008-3
Kusnanti, E. A., Sierra, E., Putra, G. G. S., Cahyadi, E. S., Haq, A., & Purwitasari, D. (2024). Indonesian Lexical Ambiguity in Machine Translation: A Literature Review. International Conference on Information Technology Research and Innovation, 59–64. https://doi.org/10.1109/icitri62858.2024.10698991
Lee, K. W., & Qian, M. (2022). Misinformation in Machine Translation: Error Categories and Levels of Recognition Difficulty. International Conference on Human-Computer Interaction, 13336, 533–545. https://doi.org/10.1007/978-3-031-05643-7_34
Lee, S., Lee, J., Moon, H., Park, C., Seo, J., Eo, S., Koo, S., & Lim, H. (2023). A Survey on Evaluation Metrics for Machine Translation. Mathematics, 11(4), 1006. https://doi.org/10.3390/math11041006
Li, J., & Armstrong, B. C. (2024). Probing the Representational Structure of Regular Polysemy via Sense Analogy Questions: Insights from Contextual Word Vectors. Cognitive Science, 48(3), 13416. https://doi.org/10.1111/cogs.13416
Man, Z., Huang, Z., Zhang, Y., Li, Y., Chen, Y., Chen, Y., & Xu, J. (2024). WDSRL: Multi-Domain Neural Machine Translation with Word-Level Domain-Sensitive Representation Learning. IEEE/ACM Transactions on Audio Speech and Language Processing, 32, 577–590. https://doi.org/10.1109/taslp.2023.3336515
Mohamed, Y. A., Khanan, A., Bashir, M., Mohamed, A. H. H. M., Adiel, M. A. E., & Elsadig, M. A. (2024). The Impact of Artificial Intelligence on Language Translation: A Review. IEEE Access, 12, 25553–25579. https://doi.org/10.1109/access.2024.3366802
Naveen, P., & Trojovský, P. (2024). Overview and Challenges of Machine Translation for Contextually Appropriate Translations. IScience, 27(10), 1–25. https://doi.org/10.1016/j.isci.2024.110878
Nemer, M. A., Azar, J., Makhoul, A., & Bourgeois, J. (2024). Leveraging AI for Enhanced Semantic Interoperability in IoT: Insights from NER Models. In International Wireless Communications and Mobile Computing (pp. 1351–1357). https://doi.org/10.1109/iwcmc61514.2024.10592578
Onan, A. (2023). SRL-ACO: A Text Augmentation Framework Based on Semantic Role Labeling and Ant Colony Optimization. Journal of King Saud University - Computer and Information Sciences, 35(7), 101611. https://doi.org/10.1016/j.jksuci.2023.101611
Oqaily, M., Kabir, M. E., Majumdar, S., Jarraya, Y., Zhang, M., Pourzandi, M., Wang, L., & Debbabi, M. (2024). ICAT+: An Interactive Customizable Anonymization Tool Using Automated Translation Through Deep Learning. IEEE Transactions on Dependable and Secure Computing, 21(4), 2799–2817. https://doi.org/10.1109/tdsc.2023.3317806
Ortiz-Garces, I., Govea, J., Andrade, R. O., & Villegas-Ch, W. (2024). Optimizing Chatbot Effectiveness through Advanced Syntactic Analysis: A Comprehensive Study in Natural Language Processing. Applied Sciences, 14(5), 1737. https://doi.org/10.3390/app14051737
Shahin, N., & Ismail, L. (2024). From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation. Artificial Intelligence Review, 57(10), 271. https://doi.org/10.1007/s10462-024-10895-z
Shekhar, S., Schwarzer, M., Dhariwal, A., & Petersen, F. C. (2025). Nasal Microbiota Transplantation: A Gateway to Novel Treatments. Trends in Microbiology, 33(3), 264–267. https://doi.org/10.1016/j.tim.2024.12.010
Sterner, B. (2022). Explaining Ambiguity in Scientific Language. Synthese, 200(5), 354. https://doi.org/10.1007/s11229-022-03792-x
Sudhi, V., Kutty, L., & Gröpler, R. (2023). Natural Language Processing for Requirements Formalization: How to Derive New Approaches? Studies in Computational Intelligence, 1091, 1–27. https://doi.org/10.1007/978-3-031-26651-5_1
Tan, F., & Wang, H. (2024). A Semantic Context-Aware Automatic Quality Scoring Method for Machine Translation Based on Pretraining Language Model. IEEE Access, 12, 72023–72033. https://doi.org/10.1109/access.2024.3402360
Viebahn, E. (2022). Copredication, Polysemy and Context-Sensitivity. Inquiry, 65(8), 1066–1082. https://doi.org/10.1080/0020174x.2020.1822911
Wang, Y. (2024). E-Learning Application in English Writing Classroom Based on Neural Machine Translation and Semantic Analysis Algorithms. Entertainment Computing, 51, 100730. https://doi.org/10.1016/j.entcom.2024.100730
Wu, H., Xu, K., & Song, L. (2024). Structure-Aware Dialogue Modeling Methods for Conversational Semantic Role Labeling. IEEE/ACM Transactions on Audio Speech and Language Processing, 32, 742–752. https://doi.org/10.1109/taslp.2023.3331576
Yang, C., & Zhang, Y. (2024). The Application of Chinese-English Machine Translation in Cultural Terminology Translation: A Case Study of Homographs and Polysemous Words. International Conference on Artificial Intelligence and Big Data, 226–231. https://doi.org/10.1109/icaibd62003.2024.10604629
Yuan, L. (2024). Semantic Role Labeling Based on Valence Structure and Deep Neural Network. IETE Journal of Research, 70(5), 5044–5052. https://doi.org/10.1080/03772063.2023.2220683
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Journal of Technology Informatics and Engineering
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).
This license allows others to copy, distribute, display, and perform the work, and derivative works based upon it, for both commercial and non-commercial purposes, as long as they credit the original author(s) and license their new creations under identical terms.
Licensed under CC BY-SA 4.0: https://creativecommons.org/licenses/by-sa/4.0/
