@inproceedings{kim-etal-2019-document,
    title = "When and Why is Document-level Context Useful in Neural Machine Translation?",
    author = "Kim, Yunsu  and
      Tran, Duc Thanh  and
      Ney, Hermann",
    editor = "Popescu-Belis, Andrei  and
      Lo{\'a}iciga, Sharid  and
      Hardmeier, Christian  and
      Xiong, Deyi",
    booktitle = "Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/D19-6503/",
    doi = "10.18653/v1/D19-6503",
    pages = "24--34",
    abstract = "Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its improvement with only a few selected examples or targeted test sets. We extensively quantify the causes of improvements by a document-level model in general test sets, clarifying the limit of the usefulness of document-level context in NMT. We show that most of the improvements are not interpretable as utilizing the context. We also show that a minimal encoding is sufficient for the context modeling and very long context is not helpful for NMT."
}