@inproceedings{zheng-etal-2019-simultaneous,
    title = "Simultaneous Translation with Flexible Policy via Restricted Imitation Learning",
    author = "Zheng, Baigong  and
      Zheng, Renjie  and
      Ma, Mingbo  and
      Huang, Liang",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/P19-1582/",
    doi = "10.18653/v1/P19-1582",
    pages = "5816--5822",
    abstract = "Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. We propose a much simpler single model that adds a {\textquotedblleft}delay{\textquotedblright} token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training. Experiments on Chinese {\ensuremath{<}}-{\ensuremath{>}} English simultaneous translation show that our work leads to flexible policies that achieve better BLEU scores and lower latencies compared to both fixed and RL-learned policies."
}