Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History

TL;DR

This paper introduces a context-aware translation system for conversational text that uses recent dialogue history and summarization to improve translation accuracy and coherence in customer support scenarios.

Contribution

The paper presents a novel translation approach that combines dialogue summarization with recent conversation history to enhance translation quality for informal, unstructured conversations.

Findings

Significant improvement in translation accuracy demonstrated.

Enhanced coherence and consistency across dialogues achieved.

Effective management of context length through summarization.

Abstract

Translating conversational text, particularly in customer support contexts, presents unique challenges due to its informal and unstructured nature. We propose a context-aware LLM translation system that leverages conversation summarization and dialogue history to enhance translation quality for the English-Korean language pair. Our approach incorporates the two most recent dialogues as raw data and a summary of earlier conversations to manage context length effectively. We demonstrate that this method significantly improves translation accuracy, maintaining coherence and consistency across conversations. This system offers a practical solution for customer support translation tasks, addressing the complexities of conversational text.