mlsanityData to 14 Oct 2026

A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis

arXiv 2306.11260 ↗First posted 20 Jun 2023cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion expression, whose diversity has great impact on model's performance. To mitigate this problem, we propose a novel and simple counterfactual data augmentation method to generate opinion expressions with reversed sentiment polarity. In particular, the integrated gradients are calculated to locate and mask the opinion expression. Then, a prompt combined with the reverse expression polarity is added to the original text, and a Pre-trained language model (PLM), T5, is finally was employed to predict the masks. The experimental results shows the proposed counterfactual data augmentation method performs better than current augmentation methods on three ABSA datasets, i.e. Laptop, Restaurant, and MAMS.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

35 of 45 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
  10. 2019Attention is not Explanationcited by 929
  11. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  12. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
23 more
  1. 2019Attention is not not Explanationcited by 636
  2. 2019Is Attention Interpretable?cited by 389
  3. 2016Understanding Neural Networks through Representation Erasurecited by 224
  4. 2015Visualizing and Understanding Neural Models in NLPcited by 200
  5. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  6. 2020Data Augmentation using Pre-trained Transformer Modelscited by 168
  7. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  8. 2018Conditional BERT Contextual Augmentationcited by 107
  9. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  10. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
  11. 2021A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysiscited by 62
  12. 2014Extraction of Salient Sentences from Labelled Documentscited by 50
  13. 2019Attentional Encoder Network for Targeted Sentiment Classificationcited by 48
  14. 2021Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTacited by 41
  15. 2020Adversarial Training for Aspect-Based Sentiment Analysis with BERTcited by 26
  16. 2023InstructABSA: Instruction Learning for Aspect Based Sentiment Analysiscited by 23
  17. 2019A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extractioncited by 18
  18. 2020Improving BERT Performance for Aspect-Based Sentiment Analysiscited by 15
  19. 2019Syntax-Aware Aspect-Level Sentiment Classification with Proximity-Weighted Convolution Networkcited by 14
  20. 2019Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classificationcited by 13
  21. 2022A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysiscited by 12
  22. 2021LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregationcited by 8
  23. 2022Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysiscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysiscited by 6
  2. 2026Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Modelscited by 0
  3. 2026Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysiscited by 0