@inproceedings{shu-nakayama-2017-empirical,
    title = "An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation",
    author = "Shu, Raphael  and
      Nakayama, Hideki",
    booktitle = "Proceedings of the First Workshop on Neural Machine Translation",
    month = aug,
    year = "2017",
    address = "Vancouver",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-3201",
    doi = "10.18653/v1/W17-3201",
    pages = "1--10",
    abstract = "Recently, the attention mechanism plays a key role to achieve high performance for Neural Machine Translation models. However, as it computes a score function for the encoder states in all positions at each decoding step, the attention model greatly increases the computational complexity. In this paper, we investigate the adequate vision span of attention models in the context of machine translation, by proposing a novel attention framework that is capable of reducing redundant score computation dynamically. The term {``}vision span{''}{'} means a window of the encoder states considered by the attention model in one step. In our experiments, we found that the average window size of vision span can be reduced by over 50{\%} with modest loss in accuracy on English-Japanese and German-English translation tasks.",
}