Papers › SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction

SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction

3 Jun 2021Findings (ACL) 2021 8arXiv:2106.01709archive 2025-07-28

Shuang Zeng, Yuting Wu, Baobao Chang

Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately represent intra- and inter-sentential relations in the same way, confounding the different patterns for predicting them. Besides, they create a document graph and use paths between entities on the graph as clues for logical reasoning. However, not all entity pairs can be connected with a path and have the correct logical reasoning paths in their graph. Thus many cases of logical reasoning cannot be covered. This paper proposes an effective architecture, SIRE, to represent intra- and inter-sentential relations in different ways. We design a new and straightforward form of logical reasoning module that can cover more logical reasoning chains. Experiments on the public datasets show SIRE outperforms the previous state-of-the-art methods. Further analysis shows that our predictions are reliable and explainable. Our code is available at https://github.com/DreamInvoker/SIRE.

PaperPDFConference PDFCode

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

Code

DreamInvoker/SIRE officialmentioned in paper 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 ExtractionLogical ReasoningRelation 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 SIRE-BERT-base F1 62.05 #19 of 62 Archive leaderboard report
Relation Extraction DocRED SIRE-BERT-base Ign F1 60.18 #19 of 62 Archive leaderboard report
Relation Extraction DocRED SIRE-GloVe F1 55.96 #49 of 62 Archive leaderboard report
Relation Extraction DocRED SIRE-GloVe Ign F1 54.04 #49 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