Home

Awesome

<h1 align="center"> RESIDE </h1> <h4 align="center">Improving Distantly-Supervised Neural Relation Extraction using Side Information</h4> <p align="center"> <a href="https://2018.emnlp.org/"><img src="http://img.shields.io/badge/EMNLP-2018-4b44ce.svg"></a> <a href="https://arxiv.org/abs/1812.04361"><img src="http://img.shields.io/badge/Paper-PDF-red.svg"></a> <a href="https://vimeo.com/305199302"><img src="http://img.shields.io/badge/Video-Vimeo-green.svg"></a> <a href="https://shikhar-vashishth.github.io/assets/pdf/reside_supp.pdf"><img src="http://img.shields.io/badge/Supplementary-PDF-B31B1B.svg"></a> <a href="https://shikhar-vashishth.github.io/assets/pdf/reside_poster.pdf"><img src="http://img.shields.io/badge/Poster-PDF-9cf.svg"></a> <a href="https://shikhar-vashishth.github.io/assets/pdf/slides_reside.pdf"><img src="http://img.shields.io/badge/Slides-PDF-orange.svg"></a> <a href="https://github.com/malllabiisc/RESIDE/blob/master/LICENSE"> <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"> </a> </p> <h2 align="center"> Overview of RESIDE <img align="center" src="./images/overview.png" alt="..."> </h2>

RESIDE first encodes each sentence in the bag by concatenating embeddings (denoted by ⊕) from Bi-GRU and Syntactic GCN for each token, followed by word attention. Then, sentence embedding is concatenated with relation alias information, which comes from the Side Information Acquisition Section, before computing attention over sentences. Finally, bag representation with entity type information is fed to a softmax classifier. Please refer to paper for more details.

Also includes implementation of PCNN, PCNN+ATT, CNN, CNN+ATT, and BGWA models.

Dependencies

Dataset:

Evaluate pretrained model:

Side Information:

Training from scratch:

Baselines:

Preprocessing a new dataset:

Running pretrained model on new samples:

Citation:

Please cite the following paper if you use this code in your work.

@inproceedings{reside2018,
  author = 	"Vashishth, Shikhar and 
  		Joshi, Rishabh and
		Prayaga, Sai Suman and
		Bhattacharyya, Chiranjib and
		Talukdar, Partha",
  title = 	"{RESIDE}: Improving Distantly-Supervised Neural Relation Extraction using Side Information",
  booktitle = 	"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
  month = 	oct # "-" # nov,
  address = 	"Brussels, Belgium",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"1257--1266",
  url = 	"http://aclweb.org/anthology/D18-1157"
}

For any clarification, comments, or suggestions please create an issue or contact Shikhar.