@inproceedings{kazemi-etal-2016-using,
    title = "Using {W}ordnet to Improve Reordering in Hierarchical Phrase-Based Statistical Machine Translation",
    author = "Kazemi, Arefeh  and
      Toral, Antonio  and
      Way, Andy",
    editor = "Fellbaum, Christiane  and
      Vossen, Piek  and
      Mititelu, Verginica Barbu  and
      Forascu, Corina",
    booktitle = "Proceedings of the 8th Global WordNet Conference (GWC)",
    month = "27--30 " # jan,
    year = "2016",
    address = "Bucharest, Romania",
    publisher = "Global Wordnet Association",
    url = "https://preview.aclanthology.org/landing_page/2016.gwc-1.24/",
    pages = "155--161",
    abstract = "We propose the use of WordNet synsets in a syntax-based reordering model for hierarchical statistical machine translation (HPB-SMT) to enable the model to generalize to phrases not seen in the training data but that have equivalent meaning. We detail our methodology to incorporate synsets' knowledge in the reordering model and evaluate the resulting WordNet-enhanced SMT systems on the English-to-Farsi language direction. The inclusion of synsets leads to the best BLEU score, outperforming the baseline (standard HPB-SMT) by 0.6 points absolute."
}