Papers › Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

21 Mar 2022Findings (ACL) 2022 5arXiv:2203.10900archive 2025-07-28

Qingyu Tan, Ruidan He, Lidong Bing, Hwee Tou Ng

Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In this paper, we propose a semi-supervised framework for DocRE with three novel components. Firstly, we use an axial attention module for learning the interdependency among entity-pairs, which improves the performance on two-hop relations. Secondly, we propose an adaptive focal loss to tackle the class imbalance problem of DocRE. Lastly, we use knowledge distillation to overcome the differences between human annotated data and distantly supervised data. We conducted experiments on two DocRE datasets. Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1.36 F1 and 1.46 Ign_F1 score on the DocRED leaderboard. Our code and data will be released at https://github.com/tonytan48/KD-DocRE.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tonytan48/kd-docre officialmentioned in paperpytorch report

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

Document-level Relation ExtractionKnowledge DistillationRelation ExtractionSentence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction DocRED KD-Rb-l F1 67.28 #2 of 62 Archive leaderboard report
Relation Extraction DocRED KD-Rb-l Ign F1 65.24 #2 of 62 Archive leaderboard report
Relation Extraction ReDocRED KD-DocRE F1 78.28 #5 of 8 Archive leaderboard report
Relation Extraction ReDocRED KD-DocRE Ign F1 77.60 #5 of 8 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.

Methods

Axial AttentionFocal LossKnowledge Distillation

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