English

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

Computation and Language 2021-05-27 v1

Abstract

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 pairs 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.

Keywords

Cite

@article{arxiv.2105.12305,
  title  = {SGPT: Semantic Graphs based Pre-training for Aspect-based Sentiment Analysis},
  author = {Yong Qian and Zhongqing Wang and Rong Xiao and Chen Chen and Haihong Tang},
  journal= {arXiv preprint arXiv:2105.12305},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2005.05635 by other authors

R2 v1 2026-06-24T02:28:17.283Z