Papersgraph - Research Paper Citation Network
HomeResearch PapersDatasetsState of the ArtPricing
Papersgraph - Research Paper Citation Network

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

  • Home
  • Research Papers
  • About

Support

  • Contact
  • Terms of Service
  • Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-4

Relationship Extraction (Distant Supervised)

3260 papers • 126 benchmarks • 313 datasets

Relationship extraction is the task of extracting semantic relationships from a text. Extracted relationships usually occur between two or more entities of a certain type (e.g. Person, Organisation, Location) and fall into a number of semantic categories (e.g. married to, employed by, lives in).

(Image credit: Papersgraph)

Relationship Extraction (Distant Supervised)

Benchmarks

These leaderboards are used to track progress in relationship-extraction-distant-supervised-9

Trend
Dataset
Best Model
Actions
New York Times Corpus
New York Times Corpus
New York Times Corpus
NYT
NYT
NYT

Libraries

i

Use these libraries to find relationship-extraction-distant-supervised-9 models and implementations

Datasets

New York Times Annotated Corpus
New York Times Annotated Corpus

Subtasks

No subtasks available.

Most implemented papers

Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

P. Talukdar, Siddhesh Khandelwal, Sharmistha Jat•Wed Apr 18 2018

Two novel word attention models for distantly- supervised relation extraction are proposed: a Bi-directional Gated Recurrent Unit based word attention model (Bi-GRU) and a combination model which combines multiple complementary models using weighted voting method for improved relation extraction.

133

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers
0
Paper Graph

Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks

Yubo Chen, Kang Liu, Jun Zhao, Daojian Zeng•Mon Aug 31 2015

This paper proposes a novel model dubbed the Piecewise Convolutional Neural Networks (PCNNs) with multi-instance learning to address the problem of wrong label problem when using distant supervision for relation extraction and adopts convolutional architecture with piecewise max pooling to automatically learn relevant features.

1095 0
Paper Graph

Joint Bootstrapping Machines for High Confidence Relation Extraction

Hinrich Schütze, Pankaj Gupta, Benjamin Roth•Mon Apr 30 2018

BEX, a new bootstrapping method that protects against semantic drift by highly effective confidence assessment, is introduced by using entity and template seeds jointly (as opposed to just one as in previous work), by expanding entities and templates in parallel and in a mutually constraining fashion in each iteration and by introducing higherquality similarity measures for templates.

20 0
Paper Graph

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

P. Talukdar, C. Bhattacharyya, Rishabh Joshi, Shikhar Vashishth, Sai Suman Prayaga•Mon Dec 10 2018

RESIDE is a distantly-supervised neural relation extraction method which utilizes additional side information from KBs for improved relation extraction and employs Graph Convolution Networks to encode syntactic information from text and improves performance even when limited side information is available.

248 0
Paper Graph

RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network

Johannes Hoffart, Kuldeep Singh, Anson Bastos, Abhishek Nadgeri, I. Mulang', Saeedeh Shekarpour•Thu Sep 17 2020

A novel method, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG) and significantly outperforms all state of the art methods on NYT Freebase and Wikidata datasets.

92 0
Paper Graph

From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension

Le Sun, Lingyong Yan, Xianpei Han, Liu Fangchao, Ning Bian•Mon Dec 07 2020

A new DS paradigm--document-based distant supervision, which models relation extraction as a document-based machine reading comprehension (MRC) task and design a new loss function--DSLoss (distant supervision loss), which can effectively train MRC models using only $\langle$ document, question, answer$ tuples, therefore noisy label problem can be inherently resolved.

2 0
Paper Graph

Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

Tianming Liang, Yang Liu, Xiaoyan Liu, Hao Zhang, Gaurav Sharma, Maozu Guo•Sun May 23 2021

A constraint graph is introduced to model the dependencies between relation labels and a constraint-aware attention module is designed in CGRE to integrate the constraint information to improve the noise immunity.

28 0
Paper Graph

KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction

Johannes Hoffart, Kuldeep Singh, Anson Bastos, Abhishek Nadgeri, I. Mulang', Saeedeh Shekarpour, V. Saraswat•Mon May 31 2021

The KGPool method dynamically expands the context with additional facts from the KG, and learns the representation of these facts (entity alias, entity descriptions, etc.) using neural methods, supplementing the sentential context.

37 0
Paper Graph

Adding a benchmark result helps the community track progress.