@inproceedings{ding-etal-2014-document,
    title = "Document-level re-ranking with soft lexical and semantic features for statistical machine translation",
    author = "Ding, Chenchen  and
      Utiyama, Masao  and
      Sumita, Eiichiro",
    editor = "Al-Onaizan, Yaser  and
      Simard, Michel",
    booktitle = "Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track",
    month = oct # " 22-26",
    year = "2014",
    address = "Vancouver, Canada",
    publisher = "Association for Machine Translation in the Americas",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2014.amta-researchers.9/",
    pages = "110--123",
    abstract = "We introduce two document-level features to polish baseline sentence-level translations generated by a state-of-the-art statistical machine translation (SMT) system. One feature uses the word-embedding technique to model the relation between a sentence and its context on the target side; the other feature is a crisp document-level token-type ratio of target-side translations for source-side words to model the lexical consistency in translation. The weights of introduced features are tuned to optimize the sentence- and document-level metrics simultaneously on the basis of Pareto optimality. Experimental results on two different schemes with different corpora illustrate that the proposed approach can efficiently and stably integrate document-level information into a sentence-level SMT system. The best improvements were approximately 0.5 BLEU on test sets with statistical significance."
}