用大模型预测未来词，提升实时翻译质量与速度
Anticipating Future with Large Language Model for Simultaneous Machine Translation
- 利用大模型预测未到来的源端词汇，提前生成目标译文
- 在相同延迟（三词）下，最高比基线提升5 BLEU
- 适合对实时性与翻译质量都有要求的场景
同步机器翻译（SMT）接收流式输入并逐步生成目标文本。现有方法主要依赖已到达的输入片段和已生成的译文。受人类口译员预判未来内容的启发，我们提出一种名为TAF（Translation by Anticipating Future）的新方法，在保持低延迟的同时提升翻译质量。其核心思想是使用大语言模型（LLM）预测未来源端词语，并在风险可控的前提下提前翻译。我们在四个语言方向上评估了TAF及多个基线方法。实验表明，TAF在翻译质量与延迟权衡上表现最优，在相同延迟（三词）条件下，最高提升5 BLEU。代码已开源：https://github.com/owaski/TAF
原文摘要 · Abstract (English)
Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods mainly use the partial utterance that has already arrived at the input and the generated hypothesis. Motivated by human interpreters' technique to forecast future words before hearing them, we propose $\textbf{T}$ranslation by $\textbf{A}$nticipating $\textbf{F}$uture (TAF), a method to improve translation quality while retraining low latency. Its core idea is to use a large language model (LLM) to predict future source words and opportunistically translate without introducing too much risk. We evaluate our TAF and multiple baselines of SMT on four language directions. Experiments show that TAF achieves the best translation quality-latency trade-off and outperforms the baselines by up to 5 BLEU points at the same latency (three words). Code is released at https://github.com/owaski/TAF
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。