Year: 2026
Type: conference-paper
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.
Institution: Monash University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140116679