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 View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

CrisJk/PA-TRP mentioned on GitHubtfSyntology: not harvested report
JiyangZhang/learning-to-reweight-in-relation-extraion mentioned on GitHubpytorchSyntology: not harvested report
SharmisthaJat/RE-DS-Word-Attention-Models mentioned on GitHubpytorchSyntology: not harvested report
malllabiisc/RESIDE mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information (arXiv:1812.04361; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
matnlp/hiclre mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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