Papers › SagDRE: Sequence-Aware Graph-Based Document-Level Relation Extraction with Adaptive Margin Loss

SagDRE: Sequence-Aware Graph-Based Document-Level Relation Extraction with Adaptive Margin Loss

16 Nov 2021ACL ARR November 2021 11archive 2025-07-28

Anonymous

Relation extraction (RE) is an important task for many natural language processing applications. Document-level relation extraction aims to extract the relations within a document and poses many challenges to the RE tasks as it requires reasoning across sentences and handling multiple relations expressed in the same document. Existing state-of-the-art document-level RE models use the graph structure to better connect long-distance correlations. In this work, we propose SagDRE model, which further considers and captures the original sequential information from the text. The proposed model learns sentence-level directional edges to capture the information flow in the document and uses the token-level sequential information to encode the shortest path from one entity to the other. In addition, we propose an adaptive margin loss to maximize the margins to separate positive and negative classes. The experimental results on datasets from various domains demonstrate the effectiveness of our proposed methods.

PaperPDFCode

Code

IAmHedgehog/SagDRE officialpytorch 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 ExtractionRelation 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 SagDRE F1 62.32 #16 of 62 Archive leaderboard report
Relation Extraction DocRED SagDRE Ign F1 60.11 #16 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