@inproceedings{zhang-feng-2021-icts,
    title = "{ICT}{'}s System for {A}uto{S}im{T}rans 2021: Robust Char-Level Simultaneous Translation",
    author = "Zhang, Shaolei  and
      Feng, Yang",
    editor = "Wu, Hua  and
      Cherry, Colin  and
      Huang, Liang  and
      He, Zhongjun  and
      Liu, Qun  and
      Elbayad, Maha  and
      Liberman, Mark  and
      Wang, Haifeng  and
      Ma, Mingbo  and
      Zhang, Ruiqing",
    booktitle = "Proceedings of the Second Workshop on Automatic Simultaneous Translation",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.autosimtrans-1.1",
    doi = "10.18653/v1/2021.autosimtrans-1.1",
    pages = "1--11",
    abstract = "Simultaneous translation (ST) outputs the translation simultaneously while reading the input sentence, which is an important component of simultaneous interpretation. In this paper, we describe our submitted ST system, which won the first place in the streaming transcription input track of the Chinese-English translation task of AutoSimTrans 2021. Aiming at the robustness of ST, we first propose char-level simultaneous translation and applied wait-k policy on it. Meanwhile, we apply two data processing methods and combine two training methods for domain adaptation. Our method enhance the ST model with stronger robustness and domain adaptability. Experiments on streaming transcription show that our method outperforms the baseline at all latency, especially at low latency, the proposed method improves about 6 BLEU. Besides, ablation studies we conduct verify the effectiveness of each module in the proposed method.",
}