@inproceedings{joulin-etal-2018-loss,
    title = "Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion",
    author = "Joulin, Armand  and
      Bojanowski, Piotr  and
      Mikolov, Tomas  and
      J{\'e}gou, Herv{\'e}  and
      Grave, Edouard",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1330/",
    doi = "10.18653/v1/D18-1330",
    pages = "2979--2984",
    abstract = "Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space. Existing works typically solve a quadratic problem to learn a orthogonal matrix aligning a bilingual lexicon, and use a retrieval criterion for inference. In this paper, we propose an unified formulation that directly optimizes a retrieval criterion in an end-to-end fashion. Our experiments on standard benchmarks show that our approach outperforms the state of the art on word translation, with the biggest improvements observed for distant language pairs such as English-Chinese."
}