@inproceedings{shi-knight-2017-speeding,
    title = "Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary",
    author = "Shi, Xing  and
      Knight, Kevin",
    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/fix-sig-urls/P17-2091/",
    doi = "10.18653/v1/P17-2091",
    pages = "574--579",
    abstract = "We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. Using the latter method, we get a 2x overall speed-up over a highly-optimized GPU implementation, without hurting BLEU. On certain low-resource language pairs, the same methods improve BLEU by 0.5 points. We also report a negative result for LSH on GPUs, due to relatively large overhead, though it was successful on CPUs. Compared with Locality Sensitive Hashing (LSH), decoding with word alignments is GPU-friendly, orthogonal to existing speedup methods and more robust across language pairs."
}