@inproceedings{thompson-koehn-2019-vecalign,
    title = "{V}ecalign: Improved Sentence Alignment in Linear Time and Space",
    author = "Thompson, Brian  and
      Koehn, Philipp",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-1136",
    doi = "10.18653/v1/D19-1136",
    pages = "1342--1348",
    abstract = "We introduce Vecalign, a novel bilingual sentence alignment method which is linear in time and space with respect to the number of sentences being aligned and which requires only bilingual sentence embeddings. On a standard German{--}French test set, Vecalign outperforms the previous state-of-the-art method (which has quadratic time complexity and requires a machine translation system) by 5 F1 points. It substantially outperforms the popular Hunalign toolkit at recovering Bible verse alignments in medium- to low-resource language pairs, and it improves downstream MT quality by 1.7 and 1.6 BLEU in Sinhala-English and Nepali-English, respectively, compared to the Hunalign-based Paracrawl pipeline.",
}