mlsanityData to 14 Oct 2026

UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning

arXiv 2211.10986 ↗First posted 20 Nov 2022cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 36 of its 59 references that are in the map. First posted on arXiv 20 Nov 2022.

Builds on

36 of 59 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  7. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  8. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  11. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  12. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
24 more
  1. 2021True Few-Shot Learning with Language Modelscited by 344
  2. 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 257
  3. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 236
  4. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  5. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  6. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  7. 2019Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysiscited by 123
  8. 2021Aspect Sentiment Quad Prediction as Paraphrase Generationcited by 100
  9. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  10. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 91
  11. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  12. 2015Effective LSTMs for Target-Dependent Sentiment Classificationcited by 82
  13. 2020The Turking Test: Can Language Models Understand Instructions?cited by 82
  14. 2018Aspect Based Sentiment Analysis with Gated Convolutional Networkscited by 65
  15. 2021A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysiscited by 62
  16. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  17. 2018A Unified Model for Opinion Target Extraction and Target Sentiment Predictioncited by 56
  18. 2019An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysiscited by 52
  19. 2019Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classificationcited by 50
  20. 2016Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysiscited by 35
  21. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  22. 2022ProQA: Structural Prompt-based Pre-training for Unified Question Answeringcited by 21
  23. 2021Open Aspect Target Sentiment Classification with Natural Language Promptscited by 20
  24. 2020Latent Opinions Transfer Network for Target-Oriented Opinion Words Extractioncited by 19

Built on by

Cited by year

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

9 papers.

  1. 2024Large Language Models Meet NLP: A Surveycited by 103
  2. 2023MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Predictioncited by 50
  3. 2024RVISA: Reasoning and Verification for Implicit Sentiment Analysiscited by 9
  4. 2024EFSA: Towards Event-Level Financial Sentiment Analysiscited by 7
  5. 2023The Limits of ChatGPT in Extracting Aspect-Category-Opinion-Sentiment Quadruples: A Comparative Analysiscited by 6
  6. 2023iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examplescited by 2
  7. 2025When LLMs Team Up: The Emergence of Collaborative Affective Computingcited by 2
  8. 2023A Weak Supervision Approach for Few-Shot Aspect Based Sentimentcited by 1
  9. 2024Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extractioncited by 0