@inproceedings{marie-fujita-2017-efficient,
    title = "Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings",
    author = "Marie, Benjamin  and
      Fujita, Atsushi",
    editor = "Barzilay, Regina  and
      Kan, Min-Yen",
    booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/P17-2062/",
    doi = "10.18653/v1/P17-2062",
    pages = "392--398",
    abstract = "We propose a new method for extracting pseudo-parallel sentences from a pair of large monolingual corpora, without relying on any document-level information. Our method first exploits word embeddings in order to efficiently evaluate trillions of candidate sentence pairs and then a classifier to find the most reliable ones. We report significant improvements in domain adaptation for statistical machine translation when using a translation model trained on the sentence pairs extracted from in-domain monolingual corpora."
}