{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:03:52Z","timestamp":1784606632913,"version":"3.55.0"},"reference-count":72,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T00:00:00Z","timestamp":1709856000000},"content-version":"vor","delay-in-days":67,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Large language models (LLMs) have demonstrated impressive capabilities in general scenarios, exhibiting a level of aptitude that approaches, in some aspects even surpasses, human-level intelligence. Among their numerous skills, the translation abilities of LLMs have received considerable attention. Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process, which might take preparatory steps to ensure high-quality translation. This work explores this possibility by proposing the MAPS framework, which stands for Multi-Aspect Prompting and Selection. Specifically, we enable LLMs first to analyze the given source sentence and induce three aspects of translation-related knowledge (keywords, topics, and relevant demonstrations) to guide the final translation process. Moreover, we employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge. Both automatic (3 LLMs \u00d7 11 directions \u00d7 2 automatic metrics) and human evaluation (preference study and MQM) demonstrate the effectiveness of MAPS. Further analysis shows that by mimicking the human translation process, MAPS reduces various translation errors such as hallucination, ambiguity, mistranslation, awkward style, untranslated text, and omission. Source code is available at https:\/\/github.com\/zwhe99\/MAPS-mt.<\/jats:p>","DOI":"10.1162\/tacl_a_00642","type":"journal-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T20:57:02Z","timestamp":1709931422000},"page":"229-246","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":78,"title":["Exploring Human-Like Translation Strategy with Large Language\n                    Models"],"prefix":"10.1162","volume":"12","author":[{"given":"Zhiwei","family":"He","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, China. zwhe.cs@sjtu.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University, China. liangt21@mails.tsinghua.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxiang","family":"Jiao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China. joelwxjiao@tencent.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuosheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China. zhangzs@sjtu.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University, China. yang.yujiu@sz.tsinghua.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China. wangrui12@sjtu.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaopeng","family":"Tu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China. zptu@tencent.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuming","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China. shumingshi@tencent.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China. brightxwang@tencent.com"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"2024030820564824400_bib1","doi-asserted-by":"publisher","first-page":"8857","DOI":"10.18653\/v1\/2023.findings-acl.564","article-title":"In-context examples selection for machine\n                        translation","volume-title":"Findings of the Association for\n                        Computational Linguistics: ACL 2023","author":"Agrawal","year":"2023"},{"key":"2024030820564824400_bib2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315619187","volume-title":"In Other Words: A Coursebook on Translation","author":"Baker","year":"2018"},{"key":"2024030820564824400_bib3","first-page":"158","article-title":"A demonstration of the nonfeasibility of\n                        fully automatic high quality translation","volume":"1","author":"Bar-Hillel","year":"1960","journal-title":"Advances\n                        in Computers"},{"key":"2024030820564824400_bib4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.01911","article-title":"Investigating the translation performance of a large\n                        multilingual language model: The case of bloom","author":"Bawden","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib5","doi-asserted-by":"publisher","DOI":"10.1353\/book6554","volume-title":"Computer-aided Translation Technology: A\n                        Practical Introduction","author":"Bowker","year":"2002"},{"key":"2024030820564824400_bib6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.12712","article-title":"Sparks of artificial general intelligence:\n                        Early experiments with gpt-4","author":"Bubeck","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib7","article-title":"Multidimensional quality metrics: A\n                        flexible system for assessing translation quality","volume-title":"Proceedings of Translating and the Computer 35","author":"Burchardt","year":"2013"},{"key":"2024030820564824400_bib8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.04227","article-title":"Video chatcaptioner: Towards the enriched\n                        spatiotemporal descriptions","author":"Chen","year":"2023","journal-title":"ArXiv\n                    preprint"},{"key":"2024030820564824400_bib9","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with\n                        90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"2024030820564824400_bib10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wmt-1.100","article-title":"The devil is in the errors: Leveraging large\n                        language models for fine-grained machine translation\n                        evaluation","author":"Fernandes","year":"2023"},{"key":"2024030820564824400_bib11","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.18653\/v1\/2022.naacl-main.100","article-title":"Quality-aware decoding for neural machine\n                        translation","volume-title":"Proceedings of the 2022 Conference\n                        of the North American Chapter of the Association for Computational\n                        Linguistics: Human Language Technologies","author":"Fernandes","year":"2022"},{"key":"2024030820564824400_bib12","doi-asserted-by":"publisher","first-page":"864","DOI":"10.18653\/v1\/2020.findings-emnlp.76","article-title":"Controlled hallucinations: Learning to\n                        generate faithfully from noisy data","volume-title":"Findings of\n                        the Association for Computational Linguistics: EMNLP 2020","author":"Filippova","year":"2020"},{"key":"2024030820564824400_bib13","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1162\/tacl_a_00437","article-title":"Experts, errors, and context: A\n                        large-scale study of human evaluation for machine\n                        translation","volume":"9","author":"Freitag","year":"2021","journal-title":"Transactions of the Association for\n                        Computational Linguistics"},{"key":"2024030820564824400_bib14","first-page":"46","article-title":"Results of WMT22 metrics shared task: Stop\n                        using BLEU \u2013 neural metrics are better and more\n                        robust","volume-title":"Proceedings of the Seventh Conference on\n                        Machine Translation (WMT)","author":"Freitag","year":"2022"},{"key":"2024030820564824400_bib15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.01398","article-title":"The unreasonable effectiveness of few-shot\n                        learning for machine translation","author":"Garcia","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.07856","article-title":"Dictionary-based phrase-level prompting of\n                        large language models for machine translation","author":"Ghazvininejad","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib17","doi-asserted-by":"publisher","DOI":"10.1075\/btl.8","volume-title":"Basic Concepts and Models for Interpreter and Translator\n                        Training","author":"Gile","year":"2009"},{"key":"2024030820564824400_bib18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00615","article-title":"Hallucinations in large multilingual\n                        translation models","author":"Guerreiro","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib19","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.18653\/v1\/2023.eacl-main.75","article-title":"Looking for a needle in a haystack: A\n                        comprehensive study of hallucinations in neural machine\n                        translation","volume-title":"Proceedings of the 17th Conference\n                        of the European Chapter of the Association for Computational\n                        Linguistics","author":"Guerreiro","year":"2023"},{"key":"2024030820564824400_bib20","doi-asserted-by":"publisher","DOI":"10.4324\/9780203501887","volume-title":"Translation: An Advanced Resource Book","author":"Hatim","year":"2004"},{"key":"2024030820564824400_bib21","doi-asserted-by":"publisher","first-page":"3662","DOI":"10.18653\/v1\/2020.findings-emnlp.327","article-title":"The box is in the pen: Evaluating commonsense reasoning in\n                        neural machine translation","volume-title":"Findings of the\n                        Association for Computational Linguistics: EMNLP 2020","author":"He","year":"2020"},{"key":"2024030820564824400_bib22","doi-asserted-by":"publisher","first-page":"6611","DOI":"10.1145\/3571730","article-title":"Bridging the data gap between training and\n                        inference for unsupervised neural machine translation","volume-title":"Proceedings of the 60th Annual Meeting of the Association for\n                        Computational Linguistics (Volume 1: Long Papers)","author":"He","year":"2022"},{"key":"2024030820564824400_bib23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.09210","article-title":"How good are gpt models at machine\n                        translation? A comprehensive evaluation","author":"Hendy","year":"2023","journal-title":"ArXiv\n                        preprint"},{"issue":"12","key":"2024030820564824400_bib24","doi-asserted-by":"publisher","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language\n                        generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"2024030820564824400_bib25","article-title":"Parrot: Translating during chat using\n                        large language models","volume-title":"ArXiv","author":"Jiao","year":"2023"},{"key":"2024030820564824400_bib26","article-title":"Is chatgpt a good translator? A\n                        preliminary study","volume-title":"ArXiv preprint","author":"Jiao","year":"2023"},{"key":"2024030820564824400_bib27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wmt-1.41","article-title":"Large language models effectively leverage\n                        document-level context for literary translation, but critical errors\n                        persist","author":"Karpinska","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib28","article-title":"Self-generated in-context learning: Leveraging\n                        auto-regressive language models as a demonstration\n                    generator","author":"Kim","year":"2022","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib29","first-page":"1","article-title":"Findings of the 2022 conference on machine\n                        translation (WMT22)","volume-title":"Proceedings of the Seventh\n                        Conference on Machine Translation (WMT)","author":"Kocmi","year":"2022"},{"key":"2024030820564824400_bib30","first-page":"478","article-title":"To ship or not to ship: An extensive\n                        evaluation of automatic metrics for machine translation","volume-title":"Proceedings of the Sixth Conference on Machine Translation","author":"Kocmi","year":"2021"},{"issue":"4","key":"2024030820564824400_bib31","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s10590-010-9076-3","article-title":"A process study of computer-aided\n                        translation","volume":"23","author":"Koehn","year":"2009","journal-title":"Machine Translation"},{"key":"2024030820564824400_bib32","first-page":"22199","article-title":"Large language models are zero-shot\n                        reasoners","volume-title":"Advances in Neural Information\n                        Processing Systems","author":"Kojima","year":"2023"},{"key":"2024030820564824400_bib33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.08635","article-title":"Self-prompting large language models for open-domain\n                        qa","author":"Li","year":"2022","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.09110","article-title":"Holistic evaluation of language\n                        models","author":"Liang","year":"2022","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.06575","article-title":"Chain-of-dictionary prompting elicits translation in large\n                        language models","author":"Hongyuan","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.1036","article-title":"New trends in machine translation using large language\n                        models: Case examples with chatgpt","author":"Lyu","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib37","article-title":"The future of MT is now and Bar-Hillel was\n                        (almost entirely) right","volume-title":"Proceedings of the\n                        Fourth Bar-Ilan Symposium on the Foundations of Artificial\n                        Intelligence","author":"Macklovitch","year":"1995"},{"key":"2024030820564824400_bib38","doi-asserted-by":"publisher","first-page":"1906","DOI":"10.18653\/v1\/2020.acl-main.173","article-title":"On faithfulness and factuality in\n                        abstractive summarization","volume-title":"Proceedings of the\n                        58th Annual Meeting of the Association for Computational\n                        Linguistics","author":"Maynez","year":"2020"},{"key":"2024030820564824400_bib39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.11490","article-title":"Boosting theory-of-mind performance in large\n                        language models via prompting","author":"Moghaddam","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.13294","article-title":"Adaptive machine translation with large language\n                        models","author":"Moslem","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib41","first-page":"27730","article-title":"Training language models to follow instructions with human\n                        feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing\n                        Systems"},{"key":"2024030820564824400_bib42","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.18653\/v1\/2020.emnlp-main.89","article-title":"ToTTo: A controlled table-to-text generation\n                        dataset","volume-title":"Proceedings of the 2020 Conference on\n                        Empirical Methods in Natural Language Processing (EMNLP)","author":"Parikh","year":"2020"},{"key":"2024030820564824400_bib43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.03442","article-title":"Generative agents: Interactive simulacra\n                        of human behavior","author":"Park","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.373","article-title":"Towards making the most of chatgpt for machine\n                        translation","author":"Peng","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.10309","article-title":"Interactive-chain-prompting: Ambiguity\n                        resolution for crosslingual conditional generation with\n                        interaction","author":"Pilault","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib46","doi-asserted-by":"publisher","DOI":"10.4324\/9781315857633","volume-title":"Exploring Translation Theories","author":"Pym","year":"2014","edition":"2nd"},{"key":"2024030820564824400_bib47","first-page":"578","article-title":"COMET-22: Unbabel-IST 2022 submission for\n                        the metrics shared task","volume-title":"Proceedings of the\n                        Seventh Conference on Machine Translation (WMT)","author":"Rei","year":"2022"},{"key":"2024030820564824400_bib48","first-page":"634","article-title":"CometKiwi: IST-unbabel 2022 submission\n                        for the quality estimation shared task","volume-title":"Proceedings of the Seventh Conference on Machine Translation\n                        (WMT)","author":"Rei","year":"2022"},{"key":"2024030820564824400_bib49","doi-asserted-by":"publisher","first-page":"7881","DOI":"10.18653\/v1\/2020.acl-main.704","article-title":"BLEURT: Learning robust metrics for text\n                        generation","volume-title":"Proceedings of the 58th Annual\n                        Meeting of the Association for Computational Linguistics","author":"Sellam","year":"2020"},{"key":"2024030820564824400_bib50","unstructured":"ShareGPT. 2023. Sharegpt: Share your\n                        wildest chatgpt conversations with one click.\n                        Available at:https:\/\/sharegpt.com\/"},{"key":"2024030820564824400_bib51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.00093","article-title":"Large language models can be easily distracted by irrelevant\n                        context","author":"Shi","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib52","article-title":"Stanford alpaca: An instruction-following\n                        llama model","author":"Taori","year":"2023"},{"key":"2024030820564824400_bib53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971","article-title":"Llama: Open and efficient foundation\n                        language models","author":"Touvron","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09288","article-title":"Llama 2: Open foundation and fine-tuned\n                        chat models","author":"Touvron","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.859","article-title":"Prompting palm for translation: Assessing\n                        strategies and performance","author":"Vilar","year":"2022","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib56","article-title":"Guofeng: A discourse-aware evaluation\n                        benchmark for language understanding, translation and\n                        generation","author":"Wang","year":"2023"},{"key":"2024030820564824400_bib57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.1036","article-title":"Document-level machine translation with\n                        large language models","author":"Wang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib58","doi-asserted-by":"publisher","first-page":"2591","DOI":"10.18653\/v1\/2022.acl-long.185","article-title":"Understanding and improving sequence-to-sequence pretraining\n                        for neural machine translation","volume-title":"Proceedings of\n                        the 60th Annual Meeting of the Association for Computational Linguistics\n                        (Volume 1: Long Papers)","author":"Wang","year":"2022"},{"key":"2024030820564824400_bib59","article-title":"Self-consistency improves chain of thought\n                        reasoning in language models","volume-title":"The Eleventh\n                        International Conference on Learning\n                    Representations","author":"Wang","year":"2023"},{"key":"2024030820564824400_bib60","doi-asserted-by":"publisher","first-page":"8640","DOI":"10.18653\/v1\/2023.acl-long.482","article-title":"Element-aware summarization with large\n                        language models: Expert-aligned evaluation and chain-of-thought\n                        method","volume-title":"Proceedings of the 61st Annual Meeting of\n                        the Association for Computational Linguistics (Volume 1: Long\n                        Papers)","author":"Wang","year":"2023"},{"key":"2024030820564824400_bib61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754","article-title":"Self-instruct: Aligning language model\n                        with self generated instructions","author":"Wang","year":"2022"},{"key":"2024030820564824400_bib62","article-title":"Emergent abilities of large language\n                        models","author":"Wei","year":"2022","journal-title":"Transactions on Machine Learning\n                        Research"},{"key":"2024030820564824400_bib63","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning\n                        in large language models","volume":"35","author":"Wei","year":"2023","journal-title":"Advances in Neural\n                        Information Processing Systems"},{"key":"2024030820564824400_bib64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.13648","article-title":"Chatgpt or grammarly? Evaluating chatgpt on grammatical error\n                        correction benchmark","author":"Hao","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.03409","article-title":"Large language models as optimizers","author":"Yang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib66","article-title":"Generate rather than retrieve: Large language\n                        models are strong context generators","volume-title":"International Conference for Learning Representation\n                    (ICLR)","author":"Wenhao","year":"2023"},{"key":"2024030820564824400_bib67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.07069","article-title":"Prompting large language model for\n                        machine translation: A case study","author":"Zhang","year":"2023","journal-title":"ArXiv\n                        preprint"},{"key":"2024030820564824400_bib68","article-title":"Automatic chain of thought prompting in\n                        large language models","volume-title":"The Eleventh International\n                        Conference on Learning Representations","author":"Zhang","year":"2023"},{"key":"2024030820564824400_bib69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.00923","article-title":"Multimodal chain-of-thought reasoning in\n                        language models","author":"Zhang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib70","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.18653\/v1\/2021.findings-acl.120","article-title":"Detecting hallucinated content in\n                        conditional neural sequence generation","volume-title":"Findings\n                        of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Zhou","year":"2021"},{"key":"2024030820564824400_bib71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.06594","article-title":"Chatgpt asks, blip-2 answers: Automatic\n                        questioning towards enriched visual descriptions","author":"Zhu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2024030820564824400_bib72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.04675","article-title":"Multilingual machine translation with\n                        large language models: Empirical results and analysis","author":"Zhu","year":"2023","journal-title":"ArXiv preprint"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00642\/2346100\/tacl_a_00642.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00642\/2346100\/tacl_a_00642.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T20:57:34Z","timestamp":1709931454000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00642\/119992\/Exploring-Human-Like-Translation-Strategy-with"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00642","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}