Papers › Document-Level Relation Extraction with Sentences Importance Estimation and Focusing

Document-Level Relation Extraction with Sentences Importance Estimation and Focusing

27 Apr 2022NAACL 2022 7arXiv:2204.12679archive 2025-07-28

Wang Xu, Kehai Chen, Lili Mou, Tiejun Zhao

Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. Recent studies typically represent the entire document by sequence- or graph-based models to predict the relations of all entity pairs. However, we find that such a model is not robust and exhibits bizarre behaviors: it predicts correctly when an entire test document is fed as input, but errs when non-evidence sentences are removed. To this end, we propose a Sentence Importance Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss, encouraging DocRE models to focus on evidence sentences. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust. Moreover, SIEF is a general framework, shown to be effective when combined with a variety of base DocRE models.

PaperPDFConference PDFCode

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

Code

xwjim/sief officialmentioned in papermentioned on GitHubpytorch 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

Dialog Relation ExtractionDocument-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
Dialog Relation Extraction DialogRE BERT+SIEF F1 (v1) 61.8 #14 of 17 Archive leaderboard report
Dialog Relation Extraction DialogRE BERT+SIEF F1c (v1) 58.4 #14 of 17 Archive leaderboard report
Relation Extraction DocRED GAIN+SIEF F1 62.29 #17 of 62 Archive leaderboard report
Relation Extraction DocRED GAIN+SIEF Ign F1 59.87 #17 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.

Methods

BASE

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