natural-language-processing-5

Document-level Relation Extraction

3260 papers • 126 benchmarks • 313 datasets

Document-level RE aim to identify the relations of various entity pairs expressed across multiple sentences.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in document-level-relation-extraction-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find document-level-relation-extraction-5 models and implementations

rudongyu/logire

2 papers 44

Datasets

No datasets available.

Subtasks

Document-level RE with incomplete labeling

Most implemented papers

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Zhenghao Liu, Xu Han, Zhiyuan Liu, Yankai Lin, Maosong Sun, Peng Li, Yuan Yao, Deming Ye, Lixin Huang, Jie Zhou•Thu Jun 13 2019

Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts.

530

Content

0

Paper Graph

Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction

Yajuan Lyu, Quan Wang, Zhendong Mao, Benfeng Xu, Yong Zhu•Fri Feb 19 2021

This work designs two alternative transformation modules inside each self-attention building block to produce attentive biases so as to adaptively regularize its attention flow, and proposes SSAN, which incorporates these structural dependencies within the standard self-Attention mechanism and throughout the overall encoding stage.

192 0

Paper Graph

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Zhijiang Guo, Wei Lu, Guoshun Nan, Ivan Sekulic•Tue May 12 2020

This work proposes a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph and develops a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning.

303 0

Paper Graph

Discriminative Reasoning for Document-level Relation Extraction

T. Zhao, Wang Xu, Kehai Chen•Wed Jun 02 2021

A novel discriminative reasoning framework is proposed to explicitly model the paths of these reasoning skills between each entity pair in this document to outperforms the previous state-of-the-art performance on the large-scale DocRE dataset.

73 0

Paper Graph

Double Graph Based Reasoning for Document-level Relation Extraction

Lei Li, Baobao Chang, Runxin Xu, Shuang Zeng•Mon Sep 28 2020

This paper proposes Graph Aggregation-and-Inference Network (GAIN) featuring double graphs, based on which GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document and proposes a novel path reasoning mechanism to infer relations between entities.

265 0

Paper Graph

Document-level Relation Extraction as Semantic Segmentation

Luo Si, Ningyu Zhang, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Huajun Chen, Xiang Chen, Xin Xie•Sun Jun 06 2021

A Document U-shaped Network for document-level relation extraction is proposed, which leverages an encoder module to capture the context information of entities and a U- shaped segmentation module over the image-style feature map to capture global interdependency among triples.

216 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

A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes

A. McCallum, Sunil Mohan, M. Torkar, Dongxu Zhang•Tue Apr 12 2022

ChemDisGene, a new dataset for training and evaluating multi-class multi-label biomedical relation extraction models, is introduced, which is both substantially larger and cleaner; it also includes annotations linking mentions to their entities.

14 0

Paper Graph

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

S. Ananiadou, Makoto Miwa, Fenia Christopoulou•Fri Aug 30 2019

This work proposes an edge-oriented graph neural model that utilises different types of nodes and edges to create a document-level graph and enables to learn intra- and inter-sentence relations using multi-instance learning internally.

216 0

Paper Graph

Adding a benchmark result helps the community track progress.