Papers › Document-Level Relation Extraction with Reconstruction

Document-Level Relation Extraction with Reconstruction

21 Dec 2020arXiv:2012.11384archive 2025-07-28

Wang Xu, Kehai Chen, Tiejun Zhao

In document-level relation extraction (DocRE), graph structure is generally used to encode relation information in the input document to classify the relation category between each entity pair, and has greatly advanced the DocRE task over the past several years. However, the learned graph representation universally models relation information between all entity pairs regardless of whether there are relationships between these entity pairs. Thus, those entity pairs without relationships disperse the attention of the encoder-classifier DocRE for ones with relationships, which may further hind the improvement of DocRE. To alleviate this issue, we propose a novel encoder-classifier-reconstructor model for DocRE. The reconstructor manages to reconstruct the ground-truth path dependencies from the graph representation, to ensure that the proposed DocRE model pays more attention to encode entity pairs with relationships in the training. Furthermore, the reconstructor is regarded as a relationship indicator to assist relation classification in the inference, which can further improve the performance of DocRE model. Experimental results on a large-scale DocRE dataset show that the proposed model can significantly improve the accuracy of relation extraction on a strong heterogeneous graph-based baseline.

PaperPDFCode

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

Code

xwjim/DocRE-Rec 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 ExtractionRelation 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 DocRED HeterGSAN+Reconstruction+BERT-base F1 59.45 #35 of 62 Archive leaderboard report
Relation Extraction DocRED HeterGSAN+Reconstruction+BERT-base Ign F1 57.12 #35 of 62 Archive leaderboard report
Relation Extraction DocRED HeterGSAN+Reconstruction F1 55.23 #52 of 62 Archive leaderboard report
Relation Extraction DocRED HeterGSAN+Reconstruction Ign F1 53.27 #52 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