Papers › Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

19 Apr 2018arXiv:1804.06987archive 2025-07-28

Sharmistha Jat, Siddhesh Khandelwal, Partha Talukdar

Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited supervision. We note that most of the sentences in the distant supervision relation extraction setting are very long and may benefit from word attention for better sentence representation. Our contributions in this paper are threefold. Firstly, we propose two novel word attention models for distantly- supervised relation extraction: (1) a Bi-directional Gated Recurrent Unit (Bi-GRU) based word attention model (BGWA), (2) an entity-centric attention model (EA), and (3) a combination model which combines multiple complementary models using weighted voting method for improved relation extraction. Secondly, we introduce GDS, a new distant supervision dataset for relation extraction. GDS removes test data noise present in all previous distant- supervision benchmark datasets, making credible automatic evaluation possible. Thirdly, through extensive experiments on multiple real-world datasets, we demonstrate the effectiveness of the proposed methods.

PaperPDFCode

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

Code

CrisJk/PA-TRP mentioned on GitHubtf report
malllabiisc/RESIDE mentioned on GitHubtfApache-2.0 report
matnlp/hiclre mentioned 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

Relation ExtractionRelationship Extraction (Distant Supervised)Sentence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Relationship Extraction (Distant Supervised) New York Times Corpus BGWA P@10% 70.9 #4 of 9 Archive leaderboard report
Relationship Extraction (Distant Supervised) New York Times Corpus BGWA P@30% 52.4 #4 of 9 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