A systematic literature review of translation memory mechanisms in technology-based translation processes
Keywords:
cat tools, fuzzy matching, retrieval mechanism, translation memory, translation processesAbstract
This study presents a systematic literature review (SLR) of Translation Memory (TM) mechanisms in technology-based translation processes, explicitly following the PRISMA framework for identification, screening, eligibility, and inclusion of studies. A total of 26 journal articles and conference papers published between 2020 and 2025 were analyzed. Findings reveal that TM operates through core mechanisms, including segmentation, storage of translation units, matching, retrieval, exact matches, fuzzy matches, and similarity measurement, which improve translation consistency, efficiency, and productivity, especially in repetitive and specialized tasks. The study also identifies limitations of TM, including dependence on database quality, reduced contextual flexibility, and challenges in capturing semantic variation with conventional matching methods. Furthermore, recent studies show that TM has evolved beyond traditional CAT tools and is increasingly integrated into neural machine translation and retrieval-augmented systems. This review contributes to the field by synthesizing current research trends, highlighting gaps in the literature, and providing recommendations for future studies to advance the integration and application of TM in modern translation workflows.References
Ben Milad, K. M. (2021). A comparison of the word similarity measurement in English-Arabic translation memory segment retrieval, including an inflectional affix intervention. Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021, 125–141. https://doi.org/10.26615/978-954-452-071-7_014
Cai, D., Wang, Y., Li, H., Lam, W., & Liu, L. (2021). Neural machine translation with monolingual translation memory. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 7307–7318. https://doi.org/10.18653/v1/2021.acl-long.567
Cheng, X., Gao, S., Liu, L., Zhao, D., & Yan, R. (2022). Neural machine translation with contrastive translation memories.
Djabri, S., Caro Quintana, R., & University of Wolverhampton, UK. (2021). Introducing linguistic transformation to improve translation memory retrieval: Results of a professional translators’ survey for Spanish, French, and Arabic. 44–50. https://doi.org/10.26615/issn.2603-2821.2021_007
Esplà-Gomis, M., Sánchez-Cartagena, V. M., Pérez-Ortiz, J. A., & Sánchez-Martínez, F. (2022). Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 7532–7543. https://doi.org/10.18653/v1/2022.emnlp-main.511
Gamal, S. (2020). The memory of knowledge: An analytical study on translators’ perceptions and assessment of CAT tools with regard to text genre. International Journal of Linguistics and Translation Studies, 1(2), 1–18. https://doi.org/10.36892/ijlts.v1i2.47
Giai, E., Poeta, N., & Turnbull, D. (2022). From server-based to web-based translation memory systems: Benchmarking, testing and implementation in STAR7: Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, 216–220. https://doi.org/10.5220/0011585400003335
Hao, H., Huang, G., Liu, L., Zhang, Z., Shi, S., & Wang, R. (2023). Rethinking translation memory augmented neural machine translation.
He, Q., Huang, G., Cui, Q., Li, L., & Liu, L. (2021). Fast and accurate neural machine translation with translation memory. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 3170–3180. https://doi.org/10.18653/v1/2021.acl-long.246
Hoang, C., Sachan, D., Mathur, P., Thompson, B., & Federico, M. (2023). Improving retrieval augmented neural machine translation by controlling source and fuzzy-match interactions. Findings of the Association for Computational Linguistics: EACL 2023, 289–295. https://doi.org/10.18653/v1/2023.findings-eacl.22
Hou, R., Liu, H., & Lepage, Y. (2024a). Leveraging knowledge from translation memory for globally and locally guiding neural machine translation.
Kim, K., Cho, M., Ryang, C., Im, J., Cho, S., Han, Y. (2021). Translation memory retrieval using Lucene. Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Methods and Applications, 684–691. https://doi.org/10.26615/978-954-452-072-4_078
Liao, H. (2025). A comparative analysis of translation quality in scientific and technical texts from the perspective of eco‐translatology.
Liu, B., & Wang, J. (2022). Analysis of strategies and skills of English translation based on coverage mechanism. Computational Intelligence and Neuroscience, 2022, 1–7. https://doi.org/10.1155/2022/7767045
Mu, Y., Reheman, A., Cao, Z., Fan, Y., Li, B., Li, Y., Xiao, T., Zhang, C., & Zhu, J. (2023). Augmenting large language model translators via translation memories. Findings of the Association for Computational Linguistics: ACL 2023, 10287–10299. https://doi.org/10.18653/v1/2023.findings-acl.653
Prasanna, A. S. D., & Latha, C. B. C. (2023). Bi-lingual machine translation approach using long short–term memory model for Asian languages. Indian Journal of Science and Technology, 16(18), 1357–1364. https://doi.org/10.17485/IJST/v16i18.176
Pu, Y. (2025). A study on the influence mechanism of the English corpus on translation quality in multilingual website translation. Applied Mathematics and Nonlinear Sciences, 10(1), 20250612. https://doi.org/10.2478/amns-2025-0612
Ranasinghe, T., & Or, C. (2020). Intelligent translation memory matching and retrieval with sentence Encoders.
Tezcan, A., Bulté, B., & Vanroy, B. (2021a). Towards a better integration of fuzzy matches in neural machine translation through data augmentation. Informatics, 8(1), 7. https://doi.org/10.3390/informatics8010007
Wang, J. (2024). Bibliometric insights into translation technology: A CiteSpace analysis of Web of Science core collection publications (2000-2024). In T. Chuanmao & D. Juntao (Eds.), Translating the future: Exploring the impact of technology and AI on modern translation studies (pp. 85–136). CSMFL Publications. https://doi.org/10.46679/9788196780593ch05
Xu, J., Crego, J., & Senellart, J. (2020). Boosting neural machine translation with similar translations. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 1580–1590. https://doi.org/10.18653/v1/2020.acl-main.144
Yang, Q. (2024). A genre-based quality evaluation of Chinese-English translation by online machine translation systems. In T. Chuanmao & D. Juntao (Eds.), Translating the future: Exploring the impact of technology and AI on modern translation studies (pp. 23–51). CSMFL Publications. https://doi.org/10.46679/9788196780593ch02
Zhang, J., Utiyama, M., Sumita, E., Neubig, G., & Nakamura, S. (2018). Guiding neural machine translation with retrieved translation pieces. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 1325–1335. https://doi.org/10.18653/v1/N18-1120
Zhang, J., Zhou, L., & Bai, W. (2024). Innovative methods for integrating translation memory and CAT tools: Enhancing intelligent support in human translation processes. Applied and Computational Engineering, 90(1), 1–7. https://doi.org/10.54254/2755-2721/90/2024MELB0054
