@inproceedings{chan-etal-2020-empirical,
    title = "An Empirical Study of Generation Order for Machine Translation",
    author = "Chan, William  and
      Stern, Mitchell  and
      Kiros, Jamie  and
      Uszkoreit, Jakob",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.emnlp-main.464/",
    doi = "10.18653/v1/2020.emnlp-main.464",
    pages = "5764--5773",
    abstract = "In this work, we present an empirical study of generation order for machine translation. Building on recent advances in insertion-based modeling, we first introduce a soft order-reward framework that enables us to train models to follow arbitrary oracle generation policies. We then make use of this framework to explore a large variety of generation orders, including uninformed orders, location-based orders, frequency-based orders, content-based orders, and model-based orders. Curiously, we find that for the WMT`14 English $\to$ German and WMT`18 English $\to$ Chinese translation tasks, order does not have a substantial impact on output quality. Moreover, for English $\to$ German, we even discover that unintuitive orderings such as alphabetical and shortest-first can match the performance of a standard Transformer, suggesting that traditional left-to-right generation may not be necessary to achieve high performance."
}