---
title: "G2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation"
authors:
  - "Baijun Ji"
  - "Zixuan Zhou"
  - "Xiangyu Duan"
  - "Yu Liu"
  - "Longbo Sun"
  - "Rupu Wei"
  - "Bohong Zhao"
doi: "10.24963/ijcai.2026/640"
url: "https://ijcai.org/proceedings/2026/640"
pdf: "https://ijcai.org/proceedings/2026/0640.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5748-5756"
track: "Main Track"
keywords:
  - "Natural Language Processing: Machine translation and multilinguality"
---

# G2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation

Baijun Ji, Zixuan Zhou, Xiangyu Duan, Yu Liu, Longbo Sun, Rupu Wei, Bohong Zhao

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5748-5756. DOI: [10.24963/ijcai.2026/640](https://doi.org/10.24963/ijcai.2026/640)

## Abstract

Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and discourse-aware context selection. However, these approaches often lack an explicit mechanism for modeling structured discourse dependencies between distant paragraphs in a document.
In this paper, we propose G²C-MT (Graph-Guided Context for Machine Translation),
which views DocMT context selection as a structured path discovery problem on a lightweight discourse graph,
rather than retrieving unstructured context sets or relying on expensive LLM-based discourse modeling.
In detail, we represent each paragraph as a node and model the relationship between each pair of nodes, considering their semantic similarity, adjacency, and keyword overlap.
Furthermore, we propose a depth-biased random walk over the graph to sample a backward context path for each target paragraph. The context path will be used to prompt a large language model (LLM) for translation.
This framework naturally supports multi-path context sampling, which can improve robustness by aggregating diverse translation candidates for discourse-ambiguous inputs.
Experiments conducted across various domains show that G²C-MT outperforms strong baselines on multiple LLMs, including DeepSeek-V3, Gemini-2.5-Flash-lite, and the Qwen-2.5/3 series.