@inproceedings{li-etal-2022-multi-granularity,
    title = "Multi-Granularity Optimization for Non-Autoregressive Translation",
    author = "Li, Yafu  and
      Cui, Leyang  and
      Yin, Yongjing  and
      Zhang, Yue",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.emnlp-main.339/",
    doi = "10.18653/v1/2022.emnlp-main.339",
    pages = "5073--5084",
    abstract = "Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviours on translation segments of various granularities and integrates feedback for backpropagation. Experiments on four WMT benchmarks show that the proposed method significantly outperforms the baseline models trained with cross-entropy loss, and achieves the best performance on WMT`16 En{\ensuremath{\Leftrightarrow}}Ro and highly competitive results on WMT`14 En{\ensuremath{\Leftrightarrow}}De for fully non-autoregressive translation."
}