@inproceedings{goto-tanaka-2017-detecting,
    title = "Detecting Untranslated Content for Neural Machine Translation",
    author = "Goto, Isao  and
      Tanaka, Hideki",
    editor = "Luong, Thang  and
      Birch, Alexandra  and
      Neubig, Graham  and
      Finch, Andrew",
    booktitle = "Proceedings of the First Workshop on Neural Machine Translation",
    month = aug,
    year = "2017",
    address = "Vancouver",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/W17-3206/",
    doi = "10.18653/v1/W17-3206",
    pages = "47--55",
    abstract = "Despite its promise, neural machine translation (NMT) has a serious problem in that source content may be mistakenly left untranslated. The ability to detect untranslated content is important for the practical use of NMT. We evaluate two types of probability with which to detect untranslated content: the cumulative attention (ATN) probability and back translation (BT) probability from the target sentence to the source sentence. Experiments on detecting untranslated content in Japanese-English patent translations show that ATN and BT are each more effective than random choice, BT is more effective than ATN, and the combination of the two provides further improvements. We also confirmed the effectiveness of using ATN and BT to rerank the n-best NMT outputs."
}