Papers › Double Graph Based Reasoning for Document-level Relation Extraction
Double Graph Based Reasoning for Document-level Relation Extraction
Shuang Zeng, Runxin Xu, Baobao Chang, Lei LI
Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs. GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/DreamInvoker/GAIN .
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Relation Extraction | DocRED | GAIN-BERT-large | F1 | 62.76 | #12 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | GAIN-BERT-large | Ign F1 | 60.31 | #12 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | GAIN-BERT | F1 | 61.24 | #27 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | GAIN-BERT | Ign F1 | 59.00 | #27 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | GAIN-GloVe | F1 | 55.08 | #53 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | GAIN-GloVe | Ign F1 | 52.66 | #53 of 62 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections