Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History
This provides a practical solution for customer support translation tasks, addressing complexities in conversational text, though it appears incremental as it builds on existing LLM methods with context management.
The paper tackles the challenge of translating informal conversational text in customer support by proposing a context-aware LLM translation system that uses conversation summarization and dialogue history for English-Korean, resulting in significantly improved translation accuracy.
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.