@inproceedings{brantley-etal-2019-non,
    title = "Non-Monotonic Sequential Text Generation",
    author = "Brantley, Kiante  and
      Cho, Kyunghyun  and
      Daum{\'e}, Hal  and
      Welleck, Sean",
    editor = "Axelrod, Amittai  and
      Yang, Diyi  and
      Cunha, Rossana  and
      Shaikh, Samira  and
      Waseem, Zeerak",
    booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W19-3620/",
    pages = "57--59",
    abstract = "Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy`s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order while achieving competitive performance with conventional left-to-right generation."
}