A Context-aware Framework for Translation-mediated Conversations
This addresses misunderstandings in translation-mediated conversations for users in task-oriented domains like customer chat and user-assistant interaction, representing an incremental improvement over existing methods.
The paper tackled the problem of translation errors in bilingual conversations by incorporating contextual information into large language model-based translation systems, resulting in TowerChat consistently outperforming state-of-the-art systems like GPT-4o and TowerInstruct across multiple metrics and language pairs.
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.