中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models

文献类型：期刊论文

作者Guo, Shoutao2,3; Zhang, Shaolei2,3; Ma, Zhengrui2,3; Zhang, Min1; Feng, Yang2,3,4
刊名IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
出版日期2025
卷号33页码:2074-2083
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
ISSN号1558-7916
DOI10.1109/TASLPRO.2025.3566220
英文摘要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.
资助项目National Natural Science Foundation of China[62376260]
WOS研究方向Acoustics ; Engineering
语种英语
WOS记录号WOS:001502204400002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/42327]  
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.Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。