资源分类
》 资源 》论文》Simultaneous Translation with Flexible Policy via Restricted Imitation Learning

Simultaneous Translation with Flexible Policy via Restricted Imitation Learning

2019-09-19 | |  74 |   36 |   0 0 0
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 “delay” token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training. Experiments on Chinese?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.

上一篇：Self-Supervised Neural Machine Translation

下一篇：STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework ?

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Joint Pose and Ex...

    Facial expression recognition (FER) is a challe...