/ResCNN_RelationExtraction

Deep Residual Learning for Weakly-Supervised Relation Extraction: https://arxiv.org/abs/1707.08866

Primary LanguagePython

ResCNN_RelationExtraction

Deep Residual Learning for Weakly-Supervised Relation Extraction: https://arxiv.org/abs/1707.08866 By Yi Yao (Darren) Huang, William Wang

Table of Contents

  1. Introduction
  2. Citation
  3. Model
  4. Result

Introduction

This work discuss about how we solve the noise from distant supervision. We propose the Deep Residual Learning for relation extraction and mitigate the influence from the noisy in semi-supervision training data. This paper is published in EMNLP2017.

Citation

If you use this model and the concept in your research, please cite:

  @InProceedings{huang-wang:2017:EMNLP2017,
      author    = {Huang, YiYao  and  Wang, William Yang},
      title     = {Deep Residual Learning for Weakly-Supervised Relation Extraction},
      booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
      month     = {September},
      year      = {2017},
      address   = {Copenhagen, Denmark},
      publisher = {Association for Computational Linguistics},
      pages     = {1804--1808},
      url       = {https://www.aclweb.org/anthology/D17-1191}
    }

Architecture

Result

Result vector1.txt: You can use Glove vector or Word2Vec. Here is the link I used in experiment : https://drive.google.com/open?id=0B-ZjKY509crKQXA0Y2FfbFJMY0E