Challenges in Context-Aware Neural Machine Translation

Challenges in Context-Aware Neural Machine Translation. Jin, L., He, J., May, J., & Ma, X. In Bouamor, H., Pino, J., & Bali, K., editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15246–15263, Singapore, December, 2023. Association for Computational Linguistics.

Paper doi abstract bibtex 2 downloads

Context-aware neural machine translation, a paradigm that involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, has given rise to a number of recent techniques. However, despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. In this work, we investigate and present several core challenges that impede progress within the field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. To address these problems, we propose a more realistic setting for document-level translation, called paragraph-to-paragraph (PARA2PARA) translation, and collect a new dataset of Chinese-English novels to promote future research.

@inproceedings{jin-etal-2023-challenges,
    title = "Challenges in Context-Aware Neural Machine Translation",
    author = "Jin, Linghao  and
      He, Jacqueline  and
      May, Jonathan  and
      Ma, Xuezhe",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.943",
    doi = "10.18653/v1/2023.emnlp-main.943",
    pages = "15246--15263",
    abstract = "Context-aware neural machine translation, a paradigm that involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, has given rise to a number of recent techniques. However, despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. In this work, we investigate and present several core challenges that impede progress within the field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. To address these problems, we propose a more realistic setting for document-level translation, called paragraph-to-paragraph (PARA2PARA) translation, and collect a new dataset of Chinese-English novels to promote future research.",
}

Downloads: 2

{"_id":"ogkhje4Z7gAEzAjcr","bibbaseid":"jin-he-may-ma-challengesincontextawareneuralmachinetranslation-2023","author_short":["Jin, L.","He, J.","May, J.","Ma, X."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Challenges in Context-Aware Neural Machine Translation","author":[{"propositions":[],"lastnames":["Jin"],"firstnames":["Linghao"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Jacqueline"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Ma"],"firstnames":["Xuezhe"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Bouamor"],"firstnames":["Houda"],"suffixes":[]},{"propositions":[],"lastnames":["Pino"],"firstnames":["Juan"],"suffixes":[]},{"propositions":[],"lastnames":["Bali"],"firstnames":["Kalika"],"suffixes":[]}],"booktitle":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","month":"December","year":"2023","address":"Singapore","publisher":"Association for Computational Linguistics","url":"https://aclanthology.org/2023.emnlp-main.943","doi":"10.18653/v1/2023.emnlp-main.943","pages":"15246–15263","abstract":"Context-aware neural machine translation, a paradigm that involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, has given rise to a number of recent techniques. However, despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. In this work, we investigate and present several core challenges that impede progress within the field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. To address these problems, we propose a more realistic setting for document-level translation, called paragraph-to-paragraph (PARA2PARA) translation, and collect a new dataset of Chinese-English novels to promote future research.","bibtex":"@inproceedings{jin-etal-2023-challenges,\n title = \"Challenges in Context-Aware Neural Machine Translation\",\n author = \"Jin, Linghao and\n He, Jacqueline and\n May, Jonathan and\n Ma, Xuezhe\",\n editor = \"Bouamor, Houda and\n Pino, Juan and\n Bali, Kalika\",\n booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n month = dec,\n year = \"2023\",\n address = \"Singapore\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://aclanthology.org/2023.emnlp-main.943\",\n doi = \"10.18653/v1/2023.emnlp-main.943\",\n pages = \"15246--15263\",\n abstract = \"Context-aware neural machine translation, a paradigm that involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, has given rise to a number of recent techniques. However, despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. In this work, we investigate and present several core challenges that impede progress within the field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. To address these problems, we propose a more realistic setting for document-level translation, called paragraph-to-paragraph (PARA2PARA) translation, and collect a new dataset of Chinese-English novels to promote future research.\",\n}\n\n","author_short":["Jin, L.","He, J.","May, J.","Ma, X."],"editor_short":["Bouamor, H.","Pino, J.","Bali, K."],"key":"jin-etal-2023-challenges","id":"jin-etal-2023-challenges","bibbaseid":"jin-he-may-ma-challengesincontextawareneuralmachinetranslation-2023","role":"author","urls":{"Paper":"https://aclanthology.org/2023.emnlp-main.943"},"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"inproceedings","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ","7qxSz9j9uMDqsXnhD"],"keywords":[],"search_terms":["challenges","context","aware","neural","machine","translation","jin","he","may","ma"],"title":"Challenges in Context-Aware Neural Machine Translation","year":2023,"downloads":2}