Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning
We present a novel approach to efficiently learn a simultaneous translation model with coupled programmer-interpreter policies. First, wepresent an algorithmic oracle to produce oracle READ/WRITE actions for training bilingual sentence-pairs using the notion of word alignments. This oracle actions are designed to capture enough information from the partial input before writing the output. Next, we perform a coupled scheduled sampling to effectively mitigate the exposure bias when learning both policies jointly with imitation learning. Experiments on six language-pairs show our method outperforms strong baselines in terms of translation quality while keeping the translation delay low.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningMachine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Streaming Translation and Transcription Through Speech-to-Text Causal Alignment
Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end mode…
Speech-to-Text TranslationMachine TranslationSimultaneous Translation with Flexible Policy via Restricted Imitation Learning
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 pro…
Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Adaptive Policy with Wait-$k$ Model for Simultaneous Translation
Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model. Traditional methods rely on either a fixed wait-$k$ policy coupled with a standalone wait-…
Machine TranslationTranslationA Generative Framework for Simultaneous Machine Translation
We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement le…
Machine Translationreinforcement-learningReinforcement Learning (RL)TranslationLEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation
Simultaneous machine translation, which aims at a real-time translation, is useful in many live scenarios but very challenging due to the trade-off between accuracy and latency. To achieve the balance for both, the model…
Machine TranslationSentenceTranslation