Discourse Graph Guided Document Translation with Large Language Models

📝 Original Info

• Title: Discourse Graph Guided Document Translation with Large Language Models
• ArXiv ID: 2511.07230
• Date: 2025-11-10
• Authors: 논문에 명시된 저자 정보가 제공되지 않았습니다. (If available, list them here.)

📝 Abstract

Adapting large language models to full document translation remains challenging due to the difficulty of capturing long-range dependencies and preserving discourse coherence throughout extended texts. While recent agentic machine translation systems mitigate context window constraints through multi-agent orchestration and persistent memory, they require substantial computational resources and are sensitive to memory retrieval strategies. We introduce TransGraph, a discourse-guided framework that explicitly models inter-chunk relationships through structured discourse graphs and selectively conditions each translation segment on relevant graph neighbourhoods rather than relying on sequential or exhaustive context. Across three document-level MT benchmarks spanning six languages and diverse domains, TransGraph consistently surpasses strong baselines in translation quality and terminology consistency while incurring significantly lower token overhead.

💡 Deep Analysis

📄 Full Content

Reference