Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models

doi:10.1109/TASLPRO.2025.3566220

	Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models
	Guo, Shoutao 1,2; Zhang, Shaolei 1,2; Ma, Zhengrui 1,2; Zhang, Min 3; Feng, Yang 1,2,4
	2025
发表期刊	IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN	1558-7916
卷号	33 页码:2074-2083
摘要	Simultaneous Machine Translation (SiMT) generates target translations in real-time while reading the source sentence. It relies on a policy to determine the optimal timing for producing translations, aiming to achieve both low response latency and high translation quality. Existing SiMT methods typically utilize the traditional Transformer architecture, employing complicated dynamic programming algorithms to jointly optimize policy decisions and translation generation. While these methods excel at determining policies, their translation capabilities are suboptimal. In contrast, Large Language Models (LLMs), trained on extensive corpora, exhibit exceptional generation capabilities but struggle to learn translation policies through traditional Transformer-based training methods. To address these limitations, we introduce Agent-SiMT, a novel framework combining the strengths of LLMs and traditional SiMT methods. Agent-SiMT contains a policy-decision agent and a translation agent. The policy-decision agent is managed by a SiMT model, which determines the policy using partial source sentences and translations. The translation agent, powered by an LLM, generates the target translation according to the policy decisions. These two agents work collaboratively to perform SiMT. Experiments demonstrate that our method attains state-of-the-art performance.
关键词	Translation Hidden Markov models Transformers Training Large language models Collaboration Vocabulary Speech processing Memory modules Machine translation Agent collaboration large language models simultaneous translation
DOI	10.1109/TASLPRO.2025.3566220
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62376260]
WOS研究方向	Acoustics ; Engineering
WOS类目	Acoustics ; Engineering, Electrical & Electronic
WOS记录号	WOS:001502204400002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42328
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Feng, Yang
作者单位	1.Chinese Acad Sci, Inst Comp Technol ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China 4.Chinese Acad Sci, Key Lab AI Safety, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Guo, Shoutao,Zhang, Shaolei,Ma, Zhengrui,et al. Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2025,33:2074-2083.
APA	Guo, Shoutao,Zhang, Shaolei,Ma, Zhengrui,Zhang, Min,&Feng, Yang.(2025).Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models.IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,33,2074-2083.
MLA	Guo, Shoutao,et al."Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models".IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 33(2025):2074-2083.