Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis
Published
2023-07-24
Yanyan Wang
,
Qun Chen
,
Murtadha Ahmed
,
Zhaoqiang Chen
,
Jing Su
,
Wei Pan
,
Zhanhuai Li
Yanyan Wang
Northwestern Polytechnical University
Qun Chen
Northwestern Polytechnical University
Murtadha Ahmed
Northwestern Polytechnical University
Zhaoqiang Chen
Northwestern Polytechnical University
Jing Su
Northwestern Polytechnical University
Wei Pan
Northwestern Polytechnical University
Zhanhuai Li
Northwestern Polytechnical University
Abstract
Recent work has shown that Aspect-Term Sentiment Analysis (ATSA) can be effectively performed by Gradual Machine Learning (GML). However, the performance of the current unsupervised solution is limited by inaccurate and insufficient knowledge conveyance. In this paper, we propose a supervised GML approach for ATSA, which can effectively exploit labeled training data to improve knowledge conveyance. It leverages binary polarity relations between instances, which can be either similar or opposite, to enable supervised knowledge conveyance. Besides the explicit polarity relations indicated by discourse structures, it also separately supervises a polarity classification DNN and a binary siamese network to extract implicit polarity relations. The proposed approach fulfills knowledge conveyance by modeling detected relations as binary features in a factor graph. Our extensive experiments on real benchmark data show that it achieves the state-of-the-art performance across all the test workloads. Our work demonstrates clearly that, in collaboration with DNN for feature extraction, GML outperforms pure DNN solutions.
Article at MIT Press
Presented at EMNLP 2023