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.
Challenges in Context-Aware Neural Machine Translation [link]Paper  doi  abstract   bibtex   4 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: 4