SGPT: Semantic Graphs based Pre-training for Aspect-based Sentiment Analysis (2105.12305v1)

Abstract: Previous studies show effective of pre-trained LLMs 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 LLMs 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 pairs and similar aspect/sentiment terms.We then optimize the pre-trained LLM 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.