Research Area:  Machine Learning

Abstract:

The stance detection task aims to classify the stance toward given documents and topics. Since the topics can be implicit in documents and unseen in training data for zero-shot settings, we propose to boost the transferability of the stance detection model by using sentiment and commonsense knowledge, which are seldom considered in previous studies. Our model includes a graph autoencoder module to obtain commonsense knowledge and a stance detection module with sentiment and commonsense. Experimental results show that our model outperforms the state-of-the-art methods on the zero-shot and few-shot benchmark dataset--VAST. Meanwhile, ablation studies prove the significance of each module in our model. Analysis of the relations between sentiment, common sense, and stance indicates the effectiveness of sentiment and common sense.

Keywords:  
Sentiment
Commonsense knowledge
Zero-shot Stance Detection
Machine Learning
Deep Learning

Author(s) Name:  Yun Luo, Zihan Liu, Yuefeng Shi, Stan Z Li, Yue Zhang

Publisher name:  arXiv.2208.08797

DOI:  10.48550/arXiv.2208.08797

Volume Information:  

Paper Link:   https://arxiv.org/abs/2208.08797