mlsanityData to 7 Oct 2026

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

arXiv 2010.00667 ↗First posted 1 Oct 2020cs.CL cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of work on improving model interpretability has just started, and many existing methods require either prior information or human annotations as additional inputs in training. To address this limitation, we propose the variational word mask (VMASK) method to automatically learn task-specific important words and reduce irrelevant information on classification, which ultimately improves the interpretability of model predictions. The proposed method is evaluated with three neural text classifiers (CNN, LSTM, and BERT) on seven benchmark text classification datasets. Experiments show the effectiveness of VMASK in improving both model prediction accuracy and interpretability.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 9; 2023: 7; 2024: 6; 2025: 3.

35 papers.

Sort:

By area:

  1. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 86
  2. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  3. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  4. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  5. 2021Logic Traps in Evaluating Attribution Scorescited by 18
  6. 2022Towards Explainable Evaluation Metrics for Natural Language Generationcited by 15
  7. 2021Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Maskscited by 12
  8. 2022Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretationcited by 12
  9. 2022Unsupervised Text Deidentificationcited by 11
  10. 2021Flexible Instance-Specific Rationalization of NLP Modelscited by 10
  11. 2024Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainabilitycited by 10
  12. 2022Human-Centric Research for NLP: Towards a Definition and Guiding Questionscited by 9
23 more
  1. 2024Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discoverycited by 8
  2. 2021Local Explanation of Dialogue Response Generationcited by 7
  3. 2021Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentationcited by 6
  4. 2022An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learningcited by 6
  5. 2023Improving Interpretability via Explicit Word Interaction Graph Layercited by 6
  6. 2024JoPA:Explaining Large Language Model's Generation via Joint Prompt Attributioncited by 6
  7. 2022Hierarchical Interpretation of Neural Text Classificationcited by 5
  8. 2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
  9. 2024Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationalescited by 5
  10. 2023A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classificationcited by 4
  11. 2025Learning Distribution-Wise Control in Representation Space for Language Modelscited by 4
  12. 2021Explaining the Road Not Takencited by 3
  13. 2022Pathologies of Pre-trained Language Models in Few-shot Fine-tuningcited by 3
  14. 2023Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verificationcited by 3
  15. 2022Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classificationcited by 2
  16. 2023Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotationscited by 2
  17. 2025SAFR: Neuron Redistribution for Interpretabilitycited by 2
  18. 2025Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verificationcited by 2
  19. 2022Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Maskingcited by 1
  20. 2024Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysiscited by 1
  21. 2023Unsupervised Text Style Transfer with Deep Generative Modelscited by 0
  22. 2023CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problemcited by 0
  23. 2024Using Interpretation Methods for Model Enhancementcited by 0