SentimentAnalysisNLP/GIN-ABSA

• Introduction
• • Requirements
  • Training
  • Citation

Introduction

This repository was used in our paper:

Extracting the Collaboration of Entity and Attribute: Gated Interactive Networks for Aspect Sentiment Analysis


Rongdi Yin, Hang Su, Bin Liang, Jiachen Du and Ruifeng Xu*. NLPCC 2020

Please cite our paper and kindly give a star for this repository if you use this code.

Requirements

• Python 3.6
• PyTorch 1.0.0

Training

• Train with command, optional arguments could be found in train.py & train_cp.py

• Run gin: ./run.sh

• Run lstm: ./run_lstm.sh

• Run bert: ./run_bert.sh

Citation

The BibTex of the citation is as follow:

@InProceedings{10.1007/978-3-030-60450-9_63,
author="Yin, Rongdi
and Su, Hang
and Liang, Bin
and Du, Jiachen
and Xu, Ruifeng",
editor="Zhu, Xiaodan
and Zhang, Min
and Hong, Yu
and He, Ruifang",
title="Extracting the Collaboration of Entity and Attribute: Gated Interactive Networks for Aspect Sentiment Analysis",
booktitle="Natural Language Processing and Chinese Computing",
year="2020",
publisher="Springer International Publishing",
address="Cham",
pages="802--814",
abstract="Aspect-based sentiment analysis (ABSA) is composed of aspect term sentiment analysis (ATSA) and aspect category sentiment analysis (ACSA). In the task of ACSA, some existing methods simply bound the aspect category (entity and attribute) as an integrated whole or adopt a randomly initialized embedding to represent the aspect category, which introduces a defective representation of aspect and leads to the ignorance of independent contextual sentiment of entity and attribute. Some other methods only consider the entity and disregard the attribute in predicting the sentiment polarity of aspect category, which leads to the ignorance of the collaboration between the entity and attribute. To this end, we propose a Gated Interactive Network (GIN) for aspect category sentiment analysis in this paper. To be specific, for each context and the corresponding aspect, we adopt two attention-based networks to learn the contextual sentiment for the entity and attribute independently and interactively. Further, based on the interactive attentions learned from entities and attributes, the coordinative gate units are exploited to reconcile and purify the sentiment features for the aspect sentiment prediction. Experimental results on two benchmark datasets demonstrate that our proposed model achieves state-of-the-art performance in the task of ACSA.",
isbn="978-3-030-60450-9"
}