mlsanityData to 14 Oct 2026

Solving Aspect Category Sentiment Analysis as a Text Generation Task

arXiv 2110.07310 ↗First posted 14 Oct 2021cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

Aspect category sentiment analysis has attracted increasing research attention. The dominant methods make use of pre-trained language models by learning effective aspect category-specific representations, and adding specific output layers to its pre-trained representation. We consider a more direct way of making use of pre-trained language models, by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output. Our method allows more direct use of pre-trained knowledge in seq2seq language models by directly following the task setting during pre-training. Experiments on several benchmarks show that our method gives the best reported results, having large advantages in few-shot and zero-shot settings.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 14 Oct 2021.

Builds on

25 of 48 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2019Language Models as Knowledge Bases?cited by 1,936
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  8. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  9. 2016Rationalizing Neural Predictionscited by 281
  10. 2019Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencecited by 122
  11. 2019Open Sesame: Getting Inside BERT's Linguistic Knowledgecited by 120
  12. 2020Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classificationcited by 98
13 more
  1. 2019Entity-Relation Extraction as Multi-Turn Question Answeringcited by 96
  2. 2014Grammar as a Foreign Languagecited by 70
  3. 2018Aspect Based Sentiment Analysis with Gated Convolutional Networkscited by 65
  4. 2016A Hierarchical Model of Reviews for Aspect-based Sentiment Analysiscited by 21
  5. 2018CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysiscited by 21
  6. 2018Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networkscited by 19
  7. 2017Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysiscited by 14
  8. 2020Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysiscited by 13
  9. 2019Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysiscited by 9
  10. 2019A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysiscited by 8
  11. 2020A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysiscited by 7
  12. 2018A Sequence-to-Sequence Model for Semantic Role Labelingcited by 5
  13. 2019A Joint Model for Aspect-Category Sentiment Analysis with Shared Sentiment Prediction Layercited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 8; 2024: 2; 2025: 3; 2026: 2.

21 papers.

Sort:

  1. 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61
  2. 2023MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Predictioncited by 50
  3. 2022A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysiscited by 12
  4. 2022Challenges for Open-domain Targeted Sentiment Analysiscited by 9
  5. 2025Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Predictioncited by 9
  6. 2022A Generative Language Model for Few-shot Aspect-Based Sentiment Analysiscited by 7
  7. 2023A Unified One-Step Solution for Aspect Sentiment Quad Predictioncited by 5
  8. 2023Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Modelcited by 5
  9. 2022DORE: Document Ordered Relation Extraction based on Generative Frameworkcited by 3
  10. 2022AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysiscited by 2
  11. 2023Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysiscited by 2
  12. 2023Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Languagecited by 1
9 more
  1. 2024E2TP: Element to Tuple Prompting Improves Aspect Sentiment Tuple Predictioncited by 1
  2. 2026A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysiscited by 1
  3. 2023From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervisioncited by 0
  4. 2023Opinion Tree Parsing for Aspect-based Sentiment Analysiscited by 0
  5. 2023An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Predictioncited by 0
  6. 2024New Benchmark Dataset and Fine-Grained Cross-Modal Fusion Framework for Vietnamese Multimodal Aspect-Category Sentiment Analysiscited by 0
  7. 2025Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysiscited by 0
  8. 2025Emotion-Enhanced Multi-Task Learning with LLMs for Aspect Category Sentiment Analysiscited by 0
  9. 2026Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysiscited by 0