Papers › Entity Structure Within and Throughout: Modeling Mention Dependencies for...
Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction
Benfeng Xu, Quan Wang, Yajuan Lyu, Yong Zhu, Zhendong Mao
Entities, as the essential elements in relation extraction tasks, exhibit certain structure. In this work, we formulate such structure as distinctive dependencies between mention pairs. We then propose SSAN, which incorporates these structural dependencies within the standard self-attention mechanism and throughout the overall encoding stage. Specifically, we design two alternative transformation modules inside each self-attention building block to produce attentive biases so as to adaptively regularize its attention flow. Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN. It significantly outperforms competitive baselines, achieving new state-of-the-art results on three popular document-level relation extraction datasets. We further provide ablation and visualization to show how the entity structure guides the model for better relation extraction. Our code is publicly available.
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 | CDR | SSANBiaffine | F1 | 68.7 | #7 of 10 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-large+Adaptation | F1 | 65.92 | #3 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-large+Adaptation | Ign F1 | 63.78 | #3 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-large | F1 | 61.42 | #22 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-large | Ign F1 | 59.47 | #22 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-base | F1 | 59.94 | #33 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-RoBERTa-base | Ign F1 | 57.71 | #33 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-BERT-base | F1 | 58.16 | #44 of 62 | Archive leaderboard | report |
| Relation Extraction | DocRED | SSAN-BERT-base | Ign F1 | 55.84 | #44 of 62 | Archive leaderboard | report |
| Relation Extraction | GDA | SSANBiaffine | F1 | 83.9 | #8 of 9 | 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