natural-language-processing-2

Joint Entity and Relation Extraction

3260 papers • 126 benchmarks • 313 datasets

Joint Entity and Relation Extraction is the task of extracting entity mentions and semantic relations between entities from unstructured text with a single model.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in joint-entity-and-relation-extraction-4

Trend

Dataset

Best Model

Actions

SciERC

WebNLG 3.0

NYT

Libraries

i

Use these libraries to find joint-entity-and-relation-extraction-4 models and implementations

Datasets

New York Times Annotated Corpus

Subtasks

No subtasks available.

Most implemented papers

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction

Hannaneh Hajishirzi, Yi Luan, Luheng He, Mari Ostendorf•Tue Aug 28 2018

The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links and supports construction of a scientific knowledge graph, which is used to analyze information in scientific literature.

753

Content

DocRED

WebNLG

CoNLL04

ADE Corpus

ACE2005

SemEval-2022 Task-12

TekGen

ACE 2005

GDA

CDR

KPI-EDGAR

2012 i2b2 Temporal Relations

RadGraph

0

A general framework for information extraction using dynamic span graphs

Hannaneh Hajishirzi, Yi Luan, Luheng He, Mari Ostendorf, David Wadden, A. Shah•Thu Apr 04 2019

This framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains and is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset.

334 0

Paper Graph

Entity, Relation, and Event Extraction with Contextualized Span Representations

Hannaneh Hajishirzi, Yi Luan, David Wadden, Ulme Wennberg•Sat Sep 07 2019

This work examines the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction (called DyGIE++) and achieves state-of-the-art results across all tasks.

656 0

Paper Graph

CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases

Jiawei Han, Zeqiu Wu, Heng Ji, Xiang Ren, Wenqi He, Meng Qu, Clare R. Voss, T. Abdelzaher•Wed Oct 26 2016

A novel domain-independent framework that jointly embeds entity mentions, relation mentions, text features and type labels into two low-dimensional spaces, and adopts a novel partial-label loss function for noisy labeled data and introduces an object "translation" function to capture the cross-constraints of entities and relations on each other.

314 0

Paper Graph

Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme

Bo Xu, Suncong Zheng, Feng Wang, Hongyun Bao, Yuexing Hao, P. Zhou•Tue Jun 06 2017

A novel tagging scheme is proposed that can convert the joint extraction task to a tagging problem, and different end-to-end models are studied to extract entities and their relations directly, without identifying entities and relations separately.

687 0

Paper Graph

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

Markus Eberts, A. Ulges•Mon Sep 16 2019

SpERT, an attention model for span-based joint entity and relation extraction, is introduced, which features entity recognition and filtering, as well as relation classification with a localized, marker-free context representation.

443 0

Paper Graph

Two Are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders

Wei Lu, Jue Wang•Wed Oct 07 2020

It is argued that it can be beneficial to design two distinct encoders to capture such two different types of information in the learning process, and proposed is the novel {\em table-sequence encoder} where two different encoder -- a table encoder and a sequence encoder are designed to help each other in the representation learning process.

246 0

Paper Graph

A Frustratingly Easy Approach for Entity and Relation Extraction

Zexuan Zhong, Danqi Chen•Mon May 31 2021

This work presents a simple pipelined approach for entity and relation extraction, and establishes the new state-of-the-art on standard benchmarks, obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders.

481 0

Paper Graph

Packed Levitated Marker for Entity and Relation Extraction

Maosong Sun, Peng Li, Yankai Lin, Deming Ye•Sun Sep 12 2021

This work proposes a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder, and proposes a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information.

131 0

Paper Graph

A sequence-to-sequence approach for document-level relation extraction

John Giorgi, Gary D Bader, Bo Wang•Sat Apr 02 2022

This paper develops a sequence-to-sequence approach, seq2rel, that can learn the subtasks of DocRE end- to-end, replacing a pipeline of task-specific components, and demonstrates that, under the model, an end-To-end approach outperforms a pipeline-based approach.

64 0

Paper Graph

Adding a benchmark result helps the community track progress.