Document-level Relation Extraction

57 papers with code • 0 benchmarks • 0 datasets

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

Libraries

Use these libraries to find Document-level Relation Extraction models and implementations
2 papers
44

Most implemented papers

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

thunlp/DocRED ACL 2019

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs.

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

PaddlePaddle/Research 20 Feb 2021

Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN.

Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction

tonytan48/re-docred 25 May 2022

We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset.

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

nanguoshun/LSR ACL 2020

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities.

Double Graph Based Reasoning for Document-level Relation Extraction

DreamInvoker/GAIN EMNLP 2020

Document-level relation extraction aims to extract relations among entities within a document.

Discriminative Reasoning for Document-level Relation Extraction

xwjim/DRN Findings (ACL) 2021

Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i. e., pattern recognition, logical reasoning, coreference reasoning, etc.)

Document-level Relation Extraction as Semantic Segmentation

zjunlp/DocuNet 7 Jun 2021

Specifically, we leverage 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.

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

johngiorgi/seq2rel BioNLP (ACL) 2022

In this paper, we develop a sequence-to-sequence approach, seq2rel, that can learn the subtasks of DocRE (entity extraction, coreference resolution and relation extraction) end-to-end, replacing a pipeline of task-specific components.

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

chanzuckerberg/chemdisgene LREC 2022

We introduce ChemDisGene, a new dataset for training and evaluating multi-class multi-label document-level biomedical relation extraction models.

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

fenchri/edge-oriented-graph IJCNLP 2019

We thus propose an edge-oriented graph neural model for document-level relation extraction.