DeepAI
Log In Sign Up

Learning Logic Rules for Document-level Relation Extraction

11/09/2021
by   Dongyu Ru, et al.
0

Document-level relation extraction aims to identify relations between entities in a whole document. Prior efforts to capture long-range dependencies have relied heavily on implicitly powerful representations learned through (graph) neural networks, which makes the model less transparent. To tackle this challenge, in this paper, we propose LogiRE, a novel probabilistic model for document-level relation extraction by learning logic rules. LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor. The rule generator is to generate logic rules potentially contributing to final predictions, and the relation extractor outputs final predictions based on the generated logic rules. Those two modules can be efficiently optimized with the expectation-maximization (EM) algorithm. By introducing logic rules into neural networks, LogiRE can explicitly capture long-range dependencies as well as enjoy better interpretation. Empirical results show that LogiRE significantly outperforms several strong baselines in terms of relation performance (1.8 F1 score) and logical consistency (over 3.3 logic score). Our code is available at https://github.com/rudongyu/LogiRE.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/29/2020

Double Graph Based Reasoning for Document-level Relation Extraction

Document-level relation extraction aims to extract relations among entit...
06/03/2021

Discriminative Reasoning for Document-level Relation Extraction

Document-level relation extraction (DocRE) models generally use graph ne...
03/21/2022

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

Document-level Relation Extraction (DocRE) is a more challenging task co...
12/06/2019

Integrating Deep Learning with Logic Fusion for Information Extraction

Information extraction (IE) aims to produce structured information from ...
10/08/2022

ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction

Document-level relation extraction with graph neural networks faces a fu...
01/29/2018

Ensemble Neural Relation Extraction with Adaptive Boosting

Relation extraction has been widely studied to extract new relational fa...
07/04/2020

Pynsett: A programmable relation extractor

This paper proposes a programmable relation extraction method for the En...