Learning Optimal Policy for Simultaneous Machine Translation via Binary Search
Simultaneous machine translation (SiMT) starts to output translation while reading the source sentence and needs a precise policy to decide when to output the generated translation. Therefore, the policy determines the number of source tokens read during the translation of each target token. However, it is difficult to learn a precise translation policy to achieve good latency-quality trade-offs, because there is no golden policy corresponding to parallel sentences as explicit supervision. In this paper, we present a new method for constructing the optimal policy online via binary search. By employing explicit supervision, our approach enables the SiMT model to learn the optimal policy, which can guide the model in completing the translation during inference. Experiments on four translation tasks show that our method can exceed strong baselines across all latency scenarios.
Code (1)
Tasks
Machine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
Simultaneous Machine Translation (SiMT) generates target translations while reading the source sentence. It relies on a policy to determine the optimal timing for reading sentences and generating translations. Existing S…
Machine TranslationSentenceTranslationNon-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation
Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming mode…
Binary ClassificationMachine TranslationTranslationSiLLM: Large Language Models for Simultaneous Machine Translation
Simultaneous Machine Translation (SiMT) generates translations while reading the source sentence, necessitating a policy to determine the optimal timing for reading and generating words. Despite the remarkable performanc…
Machine TranslationSentenceTranslationTranslation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens rem…
Action GenerationMachine TranslationSentenceTranslationLEAPT: 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