arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.04205cs.CL
收藏

一个面向翻译中介对话的上下文感知框架

A Context-aware Framework for Translation-mediated Conversations

Unbabel;Instituto de Telecomunicações(电信研究所);Instituto Superior Técnico, Universidade de Lisboa(里斯本大学技术研究所);Carnegie Mellon University(卡内基梅隆大学);ELLIS Unit Lisbon(里斯本ELLIS单位)

José Pombal, Sweta Agrawal, Patrick Fernandes, Emmanouil Zaranis, André F. T. Martins

AI总结:

提出一个上下文感知框架,通过在双语对话的训练和推理中融入上下文信息改进大模型翻译,其生成的TowerChat在多语言对上超越GPT-4o等系统并提升信息一致性。

摘要:

自动翻译系统为参与者不共享共同语言的场景提供了打破语言障碍的强大解决方案。然而,这些系统可能会引入错误,导致误解和对话破裂。一个关键问题是,当前系统未能整合解决歧义和省略细节所需的丰富上下文信息,从而导致字面的、不恰当的或不对齐的翻译。在这项工作中,我们提出了一个框架,通过在双语对话场景下的训练和推理过程中融入上下文信息,来改进基于大型语言模型的翻译系统。我们在两个面向任务的领域验证了提出的框架:客户聊天和用户-助手交互。在这两种设置中,由我们框架生成的系统——TowerChat——在多个语言对上的多种自动翻译质量指标测量下,始终比GPT-4o和TowerInstruct等最先进系统产生更好的翻译。我们还表明,生成的模型以预期且可解释的方式利用上下文,提高了所传达信息与生成翻译之间的一致性。

英文摘要:

Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation breakdown. A key issue is that current systems fail to incorporate the rich contextual information necessary to resolve ambiguities and omitted details, resulting in literal, inappropriate, or misaligned translations. In this work, we present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings during training and inference. We validate our proposed framework on two task-oriented domains: customer chat and user-assistant interaction. Across both settings, the system produced by our framework-TowerChat-consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct, as measured by multiple automatic translation quality metrics on several language pairs. We also show that the resulting model leverages context in an intended and interpretable way, improving consistency between the conveyed message and the generated translations.

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。

↑