SGPT: Semantic Graphs based Pre-training for Aspect-based Sentiment Analysis [article]

Yong Qian, Zhongqing Wang, Rong Xiao, Chen Chen, Haihong Tang
2021 arXiv   pre-print
Previous studies show effective of pre-trained language models for sentiment analysis. However, most of these studies ignore the importance of sentimental information for pre-trained models.Therefore, we fully investigate the sentimental information for pre-trained models and enhance pre-trained language models with semantic graphs for sentiment analysis.In particular, we introduce Semantic Graphs based Pre-training(SGPT) using semantic graphs to obtain synonym knowledge for aspect-sentiment
more » ... rs and similar aspect/sentiment terms.We then optimize the pre-trained language model with the semantic graphs.Empirical studies on several downstream tasks show that proposed model outperforms strong pre-trained baselines. The results also show the effectiveness of proposed semantic graphs for pre-trained model.
arXiv:2105.12305v1 fatcat:f7nyyzeeirbfvch3y5crmb2w2a