arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.06910cs.CL
收藏

Agent-SiMT:基于大语言模型的智能体辅助同声机器翻译

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

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Soochow University(苏州大学);Key Laboratory of AI Safety, Chinese Academy of Sciences(中国科学院人工智能安全重点实验室)

Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng

AI总结:

针对传统 SiMT 策略强但翻译弱、LLM 生成强却难学策略的问题,提出由 SiMT 模型决策、LLM 翻译的双智能体协作框架 Agent-SiMT,并取得最先进性能。

摘要:

同声机器翻译(SiMT)在读取源语句的同时生成目标译文。它依赖一种策略来确定读取句子和生成译文的最佳时机。现有 SiMT 方法通常采用传统 Transformer 架构,同时确定策略并生成译文。尽管这些方法擅长确定策略,但其翻译性能并不理想。相反,在大规模语料库上训练的大语言模型(LLM)具备更强的生成能力,却难以通过 SiMT 的训练方法习得翻译策略。因此,我们提出 Agent-SiMT,这是一个结合 LLM 与传统 SiMT 方法优势的框架。Agent-SiMT 包含策略决策智能体和翻译智能体。策略决策智能体由一个 SiMT 模型管理,该模型利用部分源语句和译文来确定翻译策略。翻译智能体利用 LLM,基于部分源语句生成译文。两个智能体协作完成 SiMT。实验表明,Agent-SiMT 达到了最先进性能。

英文摘要:

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 SiMT methods generally adopt the traditional Transformer architecture, which concurrently determines the policy and generates translations. While they excel at determining policies, their translation performance is suboptimal. Conversely, Large Language Models (LLMs), trained on extensive corpora, possess superior generation capabilities, but it is difficult for them to acquire translation policy through the training methods of SiMT. Therefore, we introduce Agent-SiMT, a framework combining the strengths of LLMs and traditional SiMT methods. Agent-SiMT contains the policy-decision agent and the translation agent. The policy-decision agent is managed by a SiMT model, which determines the translation policy using partial source sentence and translation. The translation agent, leveraging an LLM, generates translation based on the partial source sentence. The two agents collaborate to accomplish SiMT. Experiments demonstrate that Agent-SiMT attains state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑