mlsanityData to 14 Oct 2026

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

arXiv 2110.00171 ↗First posted 1 Oct 2021cs.CLcited by 7

Not on the map. Why?

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.

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

12 of 21 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2017Graph Attention Networkscited by 8,923
  4. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  5. 2019Designing and Interpreting Probes with Control Taskscited by 640
  6. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  7. 2017Interactive Attention Networks for Aspect-Level Sentiment Classificationcited by 91
  8. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  9. 2019Attentional Encoder Network for Targeted Sentiment Classificationcited by 48
  10. 2021Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTacited by 41
  11. 2019Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networkscited by 40
  12. 2018Aspect Level Sentiment Classification with Attention-over-Attention Neural Networkscited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
  2. 2024MSynFD: Multi-hop Syntax aware Fake News Detectioncited by 10
  3. 2023Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classificationcited by 2
  4. 2025CrosGrpsABS: Cross-Attention over Syntactic and Semantic Graphs for Aspect-Based Sentiment Analysis in a Low-Resource Languagecited by 1
  5. 2023Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Modelcited by 0
  6. 2024Amplifying Aspect-Sentence Awareness: A Novel Approach for Aspect-Based Sentiment Analysiscited by 0
  7. 2026Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimationcited by 0