[ACL'19 (Long)] GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction

A PyTorch implementation of GraphRel

Paper | Poster | Slide

Overview

GraphRel is an implementation of
"GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction"
Tsu-Jui Fu, Peng-Hsuan Li, and Wei-Yun Ma
in Annual Meeting of the Association for Computational Linguistics (ACL) 2019 (long)

In the 1st-phase, we adopt bi-RNN and GCN to extract both sequential and regional dependency word features. Given the word features, we predict relations for each word pair and the entities for all words. Then, in 2nd-phase, based on the predicted 1st-phase relations, we build complete relational graphs for each relation, to which we apply GCN on each graph to integrate each relation’s information and further consider the interaction between entities and relations.

Requirements

This code is implemented under Python3 and PyTorch.
Following libraries are also required:

• PyTorch >= 0.4
• spaCy

Usage

We use spaCy as pre-trained word embedding and dependency parser.

• GraphRel

model_graph-rel.ipynb

Resources

• NYT Dataset
• WebNLG Dataset
• This project

Citation

@inproceedings{fu2019graph-rel, 
  author = {Tsu-Jui Fu and Peng-Hsuan Li and Wei-Yun Ma}, 
  title = {GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extractionn}, 
  booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)}, 
  year = {2019} 
}

Acknowledgement

• copy_re