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

arXiv: https://arxiv.org/abs/2110.00171 · HTML: https://mlsanity.com/paper/2110.00171/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Aspect Level Sentiment Classification with Deep Memory Network](https://mlsanity.com/paper/1605.08900/) (2016)
- [Attentional Encoder Network for Targeted Sentiment Classification](https://mlsanity.com/paper/1902.09314/) (2019)
- [Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa](https://mlsanity.com/paper/2104.04986/) (2021)
- [Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks](https://mlsanity.com/paper/1909.02606/) (2019)
- [Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks](https://mlsanity.com/paper/1804.06536/) (2018)

## Built on by (most cited first, 7 of 7)

- [Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting](https://mlsanity.com/paper/2307.01709/) (2023)
- [MSynFD: Multi-hop Syntax aware Fake News Detection](https://mlsanity.com/paper/2402.14834/) (2024)
- [Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification](https://mlsanity.com/paper/2308.11447/) (2023)
- [CrosGrpsABS: Cross-Attention over Syntactic and Semantic Graphs for Aspect-Based Sentiment Analysis in a Low-Resource Language](https://mlsanity.com/paper/2505.19018/) (2025)
- [Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model](https://mlsanity.com/paper/2312.16623/) (2023)
- [Amplifying Aspect-Sentence Awareness: A Novel Approach for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2405.13013/) (2024)
- [Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimation](https://mlsanity.com/paper/2607.05260/) (2026)

## Abstract (arXiv)

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.