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

by   Ji Qi, et al.

Document-level relation extraction with graph neural networks faces a fundamental graph construction gap between training and inference - the golden graph structure only available during training, which causes that most methods adopt heuristic or syntactic rules to construct a prior graph as a pseudo proxy. In this paper, we propose ConstGCN, a novel graph convolutional network which performs knowledge-based information propagation between entities along with all specific relation spaces without any prior graph construction. Specifically, it updates the entity representation by aggregating information from all other entities along with each relation space, thus modeling the relation-aware spatial information. To control the information flow passing through the indeterminate relation spaces, we propose to constrain the propagation using transmitting scores learned from the Noise Contrastive Estimation between fact triples. Experimental results show that our method outperforms the previous state-of-the-art (SOTA) approaches on the DocRE dataset.


A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents

Distantly supervised datasets for relation extraction mostly focus on se...

Event Detection with Relation-Aware Graph Convolutional Neural Networks

Event detection (ED), a key subtask of information extraction, aims to r...

Discriminative Reasoning for Document-level Relation Extraction

Document-level relation extraction (DocRE) models generally use graph ne...

A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction

In this paper, we propose a novel edge-editing approach to extract relat...

Coarse-to-Fine Entity Representations for Document-level Relation Extraction

Document-level Relation Extraction (RE) requires extracting relations ex...

Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networks

We present a generic and trend-aware curriculum learning approach for gr...

Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference

Keyphrase extraction (KE) aims to summarize a set of phrases that accura...

Please sign up or login with your details

Forgot password? Click here to reset