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

Zeguan Xiao, Jiarun Wu, Qingliang Chen, Congjian Deng


Abstract
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). However, they ignore sequential features of the context and have not yet made the best of PLMs. In this paper, we propose a novel model, BERT4GCN, which integrates the grammatical sequential features from the PLM of BERT, and the syntactic knowledge from dependency graphs. BERT4GCN utilizes outputs from intermediate layers of BERT and positional information between words to augment GCN (Graph Convolutional Network) to better encode the dependency graphs for the downstream classification. Experimental results demonstrate that the proposed BERT4GCN outperforms all state-of-the-art baselines, justifying that augmenting GCN with the grammatical features from intermediate layers of BERT can significantly empower ABSC models.
Anthology ID:
2021.emnlp-main.724
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9193–9200
Language:
URL:
https://aclanthology.org/2021.emnlp-main.724
DOI:
10.18653/v1/2021.emnlp-main.724
Bibkey:
Cite (ACL):
Zeguan Xiao, Jiarun Wu, Qingliang Chen, and Congjian Deng. 2021. BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9193–9200, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification (Xiao et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.724.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.724.mp4
Data
SemEval-2014 Task-4