paper-with-me

Papers

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search

2023-05-22 · Shoutao Guo, Shaolei Zhang, Yang Feng

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.

📄 PDF Abstract BibTeX arXiv:2305.12774

Code (1)

ictnlp/bs-simt 공식 구현 pytorch

Tasks

Machine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models

2024-06-11 · Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang 외

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 TranslationSentenceTranslation

Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation

2025-03-28 · Zeeshan Ahmed, Frank Seide, Zhe Liu, Rastislav Rabatin 외

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 TranslationTranslation

SiLLM: Large Language Models for Simultaneous Machine Translation

2024-02-20 · Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang 외

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 TranslationSentenceTranslation

Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation

2021-11-01 · EMNLP 2021 11 · Ashkan Alinejad, Hassan S. Shavarani, Anoop Sarkar

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 TranslationSentenceTranslation

LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation

2023-03-21 · Lei Lin, Shuangtao Li, Xiaodong Shi

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