GeneZC / E2EECPE

Code and dataset for paper "End-to-end Emotion-Cause Pair Extraction via Learning to Link"

E2EECPE

This repository contains the code and dataset of the following paper:

Haolin Song, Chen Zhang, Qiuchi Li, Dawei Song. End-to-end Emotion-Cause Pair Extraction via Learning to Link. arXiv preprint arxiv:2002.10710(2020). [paper link]

Model

An overview of our model is given below:

Dataset

• The Dataset we are using is a publicly available dataset released by (Xia and Ding 2019) [dataset link]
• The pre-trained word vectors can be found here.

Requirements

• Python 3.6
• PyTorch 1.2.0

Usage

1.Clone or download this repository

[e-mail]:shl5133/E2EECPE.git

2.Download pre-trained word vectors w2v_200.txt and place it in the root path

wget -c https://raw.githubusercontent.com/NUSTM/ECPE/master/data_combine/w2v_200.txt

3.Run our model

python train.py

Citation

If you use the code in your paper, please kindly star this repo and cite our paper.

@article{song2020end,
  title={End-to-end Emotion-Cause Pair Extraction via Learning to Link},
  author={Song, Haolin and Zhang, Chen and Li, Qiuchi and Song, Dawei},
  journal={arXiv preprint arXiv:2002.10710},
  year={2020}
}