Papers › Adaptive Hinge Balance Loss for Document-Level Relation Extraction

Adaptive Hinge Balance Loss for Document-Level Relation Extraction

6 Dec 2023EMNLP 2023 12archive 2025-07-28

Jize Wang, Xinyi Le, Xiaodi Peng, Cailian Chen

Document-Level Relation Extraction aims at predicting relations between entities from multiple sentences. A common practice is to select multi-label classification thresholds to decide whether a relation exists between an entity pair. However, in the document-level task, most entity pairs do not express any relations, resulting in a highly imbalanced distribution between positive and negative classes. We argue that the imbalance problem affects threshold selection and may lead to incorrect "no-relation" predictions. In this paper, we propose to downweight the easy negatives by utilizing a distance between the classification threshold and the predicted score of each relation. Our novel Adaptive Hinge Balance Loss measures the difficulty of each relation class with the distance, putting more focus on hard, misclassified relations, i.e. the minority positive relations. Experiment results on Re-DocRED demonstrate the superiority of our approach over other balancing methods. Source codes are available at https://github.com/Jize-W/HingeABL.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

Jize-W/HingeABL mentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2023.findings-emnlp.253 (that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document-level Relation ExtractionMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationRelation Extraction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relation Extraction ReDocRED HingeABL F1 79.79 #3 of 8 Archive leaderboard report
Relation Extraction ReDocRED HingeABL Ign F1 78.82 #3 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

Focus

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