@inproceedings{jauregi-unanue-etal-2019-rewe,
    title = "{R}e{WE}: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems",
    author = "Jauregi Unanue, Inigo  and
      Zare Borzeshi, Ehsan  and
      Esmaili, Nazanin  and
      Piccardi, Massimo",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N19-1041/",
    doi = "10.18653/v1/N19-1041",
    pages = "430--436",
    abstract = "Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is jointly trained to predict the next word in the translation (categorical value) and its word embedding (continuous value). Such a joint training allows the proposed system to learn the distributional properties represented by the word embeddings, empirically improving the generalization to unseen sentences. Experiments over three translation datasets have showed a consistent improvement over a strong baseline, ranging between 0.91 and 2.4 BLEU points, and also a marked improvement over a state-of-the-art system."
}