mlsanityData to 14 Oct 2026

CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks

arXiv 2112.02714 ↗First posted 5 Dec 2021cs.CL cs.AI cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 39 of its 68 references that are in the map. First posted on arXiv 5 Dec 2021.

Builds on

39 of 68 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  10. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  11. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  12. 2017Continual Learning with Deep Generative Replaycited by 1,158
27 more
  1. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  2. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  3. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  4. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  6. 2019Contrastive Representation Distillationcited by 748
  7. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  8. 2019Three scenarios for continual learningcited by 614
  9. 2018Learning Word Vectors for 157 Languagescited by 280
  10. 2019Continual learning with hypernetworkscited by 273
  11. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  12. 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 179
  13. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  14. 2019LAMOL: LAnguage MOdeling for Lifelong Language Learningcited by 160
  15. 2019Uncertainty-based Continual Learning with Adaptive Regularizationcited by 146
  16. 2019Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencecited by 122
  17. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  18. 2020Conditional Channel Gated Networks for Task-Aware Continual Learningcited by 115
  19. 2020What Happens To BERT Embeddings During Fine-tuning?cited by 113
  20. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  21. 2018Aspect Based Sentiment Analysis with Gated Convolutional Networkscited by 65
  22. 2017Deep Generative Dual Memory Network for Continual Learningcited by 59
  23. 2019Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replaycited by 51
  24. 2018Lifelong Learning for Sentiment Classificationcited by 21
  25. 2017Lifelong Learning CRF for Supervised Aspect Extractioncited by 9
  26. 2019Forward and Backward Knowledge Transfer for Sentiment Classificationcited by 9
  27. 2017Dual Attention Network for Product Compatibility and Function Satisfiability Analysiscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 10; 2023: 7; 2024: 8; 2025: 4.

29 papers.

Sort:

By area:

  1. 2023Continual Pre-training of Language Modelscited by 198
  2. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  3. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 64
  4. 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61
  5. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  6. 2022Continual Training of Language Models for Few-Shot Learningcited by 33
  7. 2022Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detectioncited by 23
  8. 2022Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictionscited by 13
  9. 2024Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learningcited by 13
  10. 2023Class-Incremental Learning based on Label Generationcited by 11
  11. 2024Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysiscited by 11
  12. 2024CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learningcited by 11
17 more
  1. 2023Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extractioncited by 9
  2. 2022Continual Predictive Learning from Videoscited by 8
  3. 2023Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Promptcited by 8
  4. 2023InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspectivecited by 7
  5. 2022CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysiscited by 6
  6. 2025Self-Evolving LLMs via Continual Instruction Tuningcited by 4
  7. 2023CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extractioncited by 3
  8. 2024HOP to the Next Tasks and Domains for Continual Learning in NLPcited by 3
  9. 2024Continual Few-shot Event Detection via Hierarchical Augmentation Networkscited by 3
  10. 2024Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuningcited by 3
  11. 2025IRS: Incremental Relationship-guided Segmentation for Digital Pathologycited by 2
  12. 2025DoMIX: An Efficient Framework for Exploiting Domain Knowledge in Fine-Tuningcited by 2
  13. 2022DIRA: Dynamic Domain Incremental Regularised Adaptationcited by 1
  14. 2022A Framework of Customer Review Analysis Using the Aspect-Based Opinion Mining Approachcited by 1
  15. 2023Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditionscited by 1
  16. 2025Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learningcited by 1
  17. 2022A Chinese Spelling Check Framework Based on Reverse Contrastive Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
  2. 2024Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning
  3. 2023Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction
  4. 2026Dependency Reasoning for Aspect Sentiment Quadruple Prediction
  5. 2024MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction
  6. 2025Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis
  7. 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
  8. 2024Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis