{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:56:43Z","timestamp":1754153803424,"version":"3.41.2"},"reference-count":21,"publisher":"Association for Computing Machinery (ACM)","issue":"7","funder":[{"name":"Research Project of Higher Education Science of Zhejiang Sci-Tech University","award":["gjyb2302"],"award-info":[{"award-number":["gjyb2302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Large language models (LLMs), such as ChatGPT, offer powerful customized and personalized translation services, and have been increasingly integrated into various specialized fields. However, when translating low-frequency terms in professional domains, LLMs frequently produce mistranslations and omissions due to insufficient training of term mapping relationships. We calculate the mapping probabilities of keywords from approximately 80,000 bilingual (Chinese-to-English) academic articles in the textile domain and apply them through in-context learning (ICL) to enhance the textile-specific translation performance of five LLMs: GPT-4o-Mini, Grok-3, Claude-3.7-Sonnet-all, Gemini-2.0-Flash, and Deepseek-Chat. The results indicated that providing LLMs with simple in-context learning prompts containing the most probable English translations for 14,373 Chinese textile terms led to approximately 40% improvement in terminology translation accuracy while significantly reducing mistranslations and omissions. Building on this foundation, we introduce chain-of-thought (CoT) mechanisms to terminology translation tasks, simulating human translators\u2019 reasoning processes to address the contextual limitations of traditional dictionary-based methods. Our developed textile AI-enhanced translation system, based on mapping probabilities and in-context learning frameworks, effectively avoids common errors in textile terminology translation that persist.<\/jats:p>","DOI":"10.1145\/3746227","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T05:49:15Z","timestamp":1750916955000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Textile AI-Enhanced Translation System Based on Mapping Probability and In-context Learning"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0032-338X","authenticated-orcid":false,"given":"Weilin","family":"Hu","sequence":"first","affiliation":[{"name":"College of Textile Science and Engineering (International Institute of Silk), Zhejiang Sci-Tech University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0542-7478","authenticated-orcid":false,"given":"Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Textile Science and Engineering (International Institute of Silk), Zhejiang Sci-Tech University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2080-0948","authenticated-orcid":false,"given":"Qizheng","family":"Li","sequence":"additional","affiliation":[{"name":"Periodicals Agency, Zhejiang Sci-Tech University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5925-7264","authenticated-orcid":false,"given":"Xiaona","family":"Yu","sequence":"additional","affiliation":[{"name":"Periodicals Agency, Zhejiang Sci-Tech University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6704-5624","authenticated-orcid":false,"given":"Chengyan","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Textile Science and Engineering (International Institute of Silk), Zhejiang Sci-Tech University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"issue":"1","key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1162\/tacl_a_00730","article-title":"Salute the classic: Revisiting challenges of machine translation in the age of large language models","volume":"13","author":"Pang Jianhui","year":"2025","unstructured":"Jianhui Pang, Fanghua Ye, Derek Fai Wong, Dian Yu, Shuming Shi, Zhaopeng Tu, and Longyue Wang. 2025. Salute the classic: Revisiting challenges of machine translation in the age of large language models. Transactions of the Association for Computational Linguistics 13, 1 (2025), 73\u201395.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/info14100574"},{"key":"e_1_3_1_4_2","first-page":"1059","article-title":"Translate-and-revise: Boosting large language models for constrained translation","author":"Huang Pengcheng","year":"2024","unstructured":"Pengcheng Huang, Yongyu Mu, Yuzhang Wu, Bei Li, Chunyang Xiao, and Tong Xiao. 2024. Translate-and-revise: Boosting large language models for constrained translation. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics. 1059\u20131074.","journal-title":"Proceedings of the 23rd Chinese National Conference on Computational Linguistics"},{"key":"e_1_3_1_5_2","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Jingyuan Ma Rui Li Heming Xia Jingjing Xu Zhiyong Wu Tianyu Liu Baobao Chang Xu Sun Lei Li and Zhifang Sui. 2022. A survey on in-context learning. arXiv preprint: 2301.00234 (2022)."},{"key":"e_1_3_1_6_2","first-page":"76930","article-title":"Many-shot in-context learning","author":"Agarwal Rishabh","year":"2024","unstructured":"Rishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D. Co-Reyes, Eric Chu, Feryal Behbahani, Aleksandra Faust, and Hugo Larochelle. 2024. Many-shot in-context learning. In Proceedings of the 2024 Advances in Neural Information Processing Systems. 76930\u201376966.","journal-title":"Proceedings of the 2024 Advances in Neural Information Processing Systems"},{"issue":"4","key":"e_1_3_1_7_2","first-page":"4051","article-title":"A review of generalized zero-shot learning methods","volume":"45","author":"Pourpanah Farhad","year":"2022","unstructured":"Farhad Pourpanah, Moloud Abdar, Yuxuan Luo, Xinlei Zhou, Ran Wang, and Chee Peng Lim. 2022. A review of generalized zero-shot learning methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4051\u20134070.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_8_2","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. In Proceedings of the 2022 Advances in Neural Information Processing Systems. 1950\u20131965.","journal-title":"Proceedings of the 2022 Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_9_2","unstructured":"Maciej Besta Florim Memedi Zhenyu Zhang Robert Gerstenberger Guangyuan Piao Nils Blach Piotr Nyczyk Marcin Copik Grzegorz Kwa\u015bniewski J\u00fcrgen M\u00fcller Lukas Gianinazzi Ales Kubicek Hubert Niewiadomski Aidan O'Mahony Onur Mutlu Torsten Hoefler. 2024. Demystifying chains trees and graphs of thoughts. arXiv preprint: 2401.14295 (2024)."},{"key":"e_1_3_1_10_2","first-page":"15685","article-title":"Teaching large language models to translate on low-resource languages with textbook prompting","author":"Guo Ping","year":"2024","unstructured":"Ping Guo, Yubing Ren, Yue Hu, Yunpeng Li, Jiarui Zhang, Xingsheng Zhang, and Heyan Huang. 2024. Teaching large language models to translate on low-resource languages with textbook prompting. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. 15685\u201315697.","journal-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation"},{"key":"e_1_3_1_11_2","unstructured":"Marjan Ghazvininejad Hila Gonen and Luke Zettlemoyer. 2023. Dictionary-based phrase-level prompting of large language models for machine translation. arXiv preprint: 2302.07856 (2023)."},{"key":"e_1_3_1_12_2","unstructured":"Armel Zebaze Beno\u00eet Sagot and Rachel Bawden. 2024. In-context example selection via similarity search improves low-resource machine translation. arXiv preprint: 2408.00397 (2024)."},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","first-page":"19488","DOI":"10.1609\/aaai.v38i17.29920","article-title":"Teaching large language models to translate with comparison","author":"Zeng Jiali","year":"2024","unstructured":"Jiali Zeng, Fandong Meng, Yongjing Yin, and Jie Zhou. 2024. Teaching large language models to translate with comparison. In Proceedings of the AAAI Conference on Artificial Intelligence. 19488\u201319496.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_1_14_2","unstructured":"Haoran Xu Young Jin Kim Amr Sharaf and Hany Hassan Awadalla. 2023. A paradigm shift in machine translation: Boosting translation performance of large language models. arXiv preprint: 2309.11674 (2023)."},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Vivek Iyer Pinzhen Chen and Alexandra Birch. 2023. Towards effective disambiguation for machine translation with large language models. arXiv preprint: 2309.11668 (2023).","DOI":"10.18653\/v1\/2023.wmt-1.44"},{"key":"e_1_3_1_16_2","unstructured":"OpenAI. 2025. GPT-4o mini: Advancing cost-efficient intelligence. Retrieved June 18 2025 from https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence\/"},{"key":"e_1_3_1_17_2","unstructured":"xAI. 2025. Grok 3 Beta \u2014 The age of reasoning agents. Retrieved June 18 2025 from https:\/\/x.ai\/news\/grok-3"},{"key":"e_1_3_1_18_2","unstructured":"Anthropic. 2025. Claude 3.7 Sonnet system card. Retrieved June 18 2025 from https:\/\/assets.anthropic.com\/m\/785e231869ea8b3b\/original\/claude-3-7-sonnet-system-card.pdf"},{"key":"e_1_3_1_19_2","article-title":"Introducing gemini 2.0: Our new AI model for the agentic era","author":"Google","year":"2024","unstructured":"Google. 2024. Introducing gemini 2.0: Our new AI model for the agentic era. The Keyword. Retrieved June 18, 2025 from https:\/\/blog.google\/technology\/google-deepmind\/google-gemini-ai-update-december-2024\/","journal-title":"The Keyword"},{"key":"e_1_3_1_20_2","unstructured":"Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng et al. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint: 2401.02954 (2024)."},{"key":"e_1_3_1_21_2","unstructured":"\u5218\u5c0f\u6684. 2023. \u821e\u53f0\u670d\u88c5\u4e2d\u9762\u6599\u518d\u9020\u7684\u8bbe\u8ba1\u5e94\u7528. \u7eba\u7ec7\u62a5\u544a 42 7 (2023) 43\u201345."},{"issue":"2","key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1049\/cje.2020.01.001","article-title":"A short text classification method based on N-gram and CNN","volume":"29","year":"2020","unstructured":"Haitao Wang, Jie He, Xiaohong Zhang, Shufen Liu 2020. A short text classification method based on N-gram and CNN. Chinese Journal of Electronics 29, 2 (2020), 248\u2013254.","journal-title":"Chinese Journal of Electronics"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:56:50Z","timestamp":1753275410000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,23]]},"references-count":21,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3746227"],"URL":"https:\/\/doi.org\/10.1145\/3746227","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2025,7,23]]},"assertion":[{"value":"2024-11-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}