mlsanityData to 14 Oct 2026

Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis

arXiv 2203.16369 ↗First posted 30 Mar 2022cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence. While pre-trained language models such as BERT have achieved great success, incorporating dynamic semantic changes into ABSA remains challenging. To this end, in this paper, we propose to address this problem by Dynamic Re-weighting BERT (DR-BERT), a novel method designed to learn dynamic aspect-oriented semantics for ABSA. Specifically, we first take the Stack-BERT layers as a primary encoder to grasp the overall semantic of the sentence and then fine-tune it by incorporating a lightweight Dynamic Re-weighting Adapter (DRA). Note that the DRA can pay close attention to a small region of the sentences at each step and re-weigh the vitally important words for better aspect-aware sentiment understanding. Finally, experimental results on three benchmark datasets demonstrate the effectiveness and the rationality of our proposed model and provide good interpretable insights for future semantic modeling.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 24 of its 61 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

24 of 61 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  6. 2016Image Captioning with Semantic Attentioncited by 260
  7. 2019Understanding and Improving Layer Normalizationcited by 217
  8. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  9. 2019Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencecited by 122
  10. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  11. 2017Interactive Attention Networks for Aspect-Level Sentiment Classificationcited by 91
  12. 2015Effective LSTMs for Target-Dependent Sentiment Classificationcited by 82
12 more
  1. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  2. 2016Deep Learning Human Mind for Automated Visual Classificationcited by 77
  3. 2019Attentional Encoder Network for Targeted Sentiment Classificationcited by 48
  4. 2018Transformation Networks for Target-Oriented Sentiment Classificationcited by 47
  5. 2019Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networkscited by 40
  6. 2018Aspect Level Sentiment Classification with Attention-over-Attention Neural Networkscited by 24
  7. 2019Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysiscited by 16
  8. 2020Understanding Pre-trained BERT for Aspect-based Sentiment Analysiscited by 9
  9. 2019A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysiscited by 8
  10. 2020Bi-directional Cognitive Thinking Network for Machine Reading Comprehensioncited by 3
  11. 2019A Dynamic and Cooperative Tracking System for Crowdfundingcited by 1
  12. 2021SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 4; 2025: 2; 2026: 1.

10 papers.

  1. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  2. 2025Parameter-Efficient Fine-Tuning for Foundation Modelscited by 45
  3. 2024Recent Advances in Multimodal Affective Computing: An NLP Perspectivecited by 13
  4. 2022Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classificationcited by 6
  5. 2024Towards Few-shot Self-explaining Graph Neural Networkscited by 4
  6. 2023AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Rankingcited by 2
  7. 2025WDMIR: Wavelet-Driven Multimodal Intent Recognitioncited by 2
  8. 2023Contrastive variational information bottleneck for aspect-based sentiment analysiscited by 1
  9. 2026Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integrationcited by 1
  10. 2024Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Modelscited by 0