@inproceedings{madhyastha-espana-bonet-2017-learning,
    title = "Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation",
    author = "Madhyastha, Pranava Swaroop  and
      Espa{\~n}a-Bonet, Cristina",
    editor = "Blunsom, Phil  and
      Bordes, Antoine  and
      Cho, Kyunghyun  and
      Cohen, Shay  and
      Dyer, Chris  and
      Grefenstette, Edward  and
      Hermann, Karl Moritz  and
      Rimell, Laura  and
      Weston, Jason  and
      Yih, Scott",
    booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-2617/",
    doi = "10.18653/v1/W17-2617",
    pages = "139--145",
    abstract = "We propose a simple log-bilinear softmax-based model to deal with vocabulary expansion in machine translation. Our model uses word embeddings trained on significantly large unlabelled monolingual corpora and learns over a fairly small, word-to-word bilingual dictionary. Given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language using the trained bilingual embeddings. We integrate these translation options into a standard phrase-based statistical machine translation system and obtain consistent improvements in translation quality on the English{--}Spanish language pair. When tested over an out-of-domain testset, we get a significant improvement of 3.9 BLEU points."
}