BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification

no code implementations • EMNLP 2021 • Zeguan Xiao, Jiarun Wu, Qingliang Chen, Congjian Deng

Graph-based Aspect-based Sentiment Classification (ABSC) approaches have yielded state-of-the-art results, expecially when equipped with contextual word embedding from pre-training language models (PLMs).

Sentiment Analysis Sentiment Classification