Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

by   Wenxuan Zhou, et al.

Document-level relation extraction (RE) poses new challenges compared to its sentence-level RE counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with multiple possible relations. In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multilabel and multi-entity problems. The adaptive thresholding replaces the global threshold for multi-label classification in the prior work by a learnable entities-dependent threshold. The localized context pooling directly transfers attention from pre-trained language models to locate relevant context that is useful to decide the relation. We experiment on three document-level RE benchmark datasets: DocRED, a recently released large-scale RE dataset, and two datasets CDR and GDA in the biomedical domain. Our ATLOP (Adaptive Thresholding and Localized cOntext Pooling) model achieves an F1 score of 63.4; and also significantly outperforms existing models on both CDR and GDA.



page 1

page 2

page 3

page 4


None Class Ranking Loss for Document-Level Relation Extraction

Document-level relation extraction (RE) aims at extracting relations amo...

Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction

Compared with traditional sentence-level relation extraction, document-l...

Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning

Document-level Relation Extraction (DRE) aims to recognize the relations...

Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

Document-level Relation Extraction (DocRE) is a more challenging task co...

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

We introduce SpERT, an attention model for span-based joint entity and r...

Predicting Document Coverage for Relation Extraction

This paper presents a new task of predicting the coverage of a text docu...

On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning

Deep learning models have achieved state-of-the-art performances on many...

Code Repositories


Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling".

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.