mlsanityData to 7 Oct 2026

Deriving Machine Attention from Human Rationales

arXiv 1808.09367 ↗First posted 28 Aug 2018cs.CLcited by 54

Not on the map. Why?

Abstract (arXiv)

Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and map them into continuous attention. Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones. Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention. Our empirical results validate this hypothesis and show that our approach delivers significant gains over state-of-the-art baselines, yielding over 15% average error reduction on benchmark datasets.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 9; 2023: 7; 2024: 10; 2025: 11.

54 papers.

Sort:

  1. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  2. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  3. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  4. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  5. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  6. 2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
  7. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  8. 2023D-Separation for Causal Self-Explanationcited by 21
  9. 2021Rationalization through Conceptscited by 19
  10. 2021SPECTRA: Sparse Structured Text Rationalizationcited by 19
  11. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  12. 2022FR: Folded Rationalization with a Unified Encodercited by 18
38 more
  1. 2021Predict then Interpolate: A Simple Algorithm to Learn Stable Classifierscited by 16
  2. 2022A survey on improving NLP models with human explanationscited by 15
  3. 2023Enhancing the Rationale-Input Alignment for Self-explaining Rationalizationcited by 15
  4. 2021Distribution Matching for Rationalizationcited by 14
  5. 2023Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraintcited by 14
  6. 2023MGR: Multi-generator Based Rationalizationcited by 12
  7. 2024CREW: Facilitating Human-AI Teaming Researchcited by 11
  8. 2022Making a (Counterfactual) Difference One Rationale at a Timecited by 10
  9. 2024Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Modelscited by 10
  10. 2021Exploring Distantly-Labeled Rationales in Neural Network Modelscited by 8
  11. 2024Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discoverycited by 8
  12. 2021Few-Shot Semantic Parsing for New Predicatescited by 7
  13. 2022Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detectioncited by 7
  14. 2024A Survey on Human-AI Collaboration with Large Foundation Modelscited by 7
  15. 2021Nutri-bullets: Summarizing Health Studies by Composing Segmentscited by 6
  16. 2024Plausible Extractive Rationalization through Semi-Supervised Entailment Signalcited by 6
  17. 2025Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilizationcited by 6
  18. 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasetscited by 6
  19. 2021Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attentioncited by 5
  20. 2021Cross-language Sentence Selection via Data Augmentation and Rationale Trainingcited by 5
  21. 2022It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifierscited by 5
  22. 2024Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationalescited by 5
  23. 2024MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extractioncited by 4
  24. 2021Attention Forcing for Machine Translationcited by 3
  25. 2022Towards Structuring Real-World Data at Scale: Deep Learning for Extracting Key Oncology Information from Clinical Text with Patient-Level Supervisioncited by 3
  26. 2023You Only Forward Once: Prediction and Rationalization in A Single Forward Passcited by 2
  27. 2024Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Offcited by 2
  28. 2025Boosting Explainability through Selective Rationalization in Pre-trained Language Modelscited by 2
  29. 2025SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Modelscited by 2
  30. 2021Interpreting and improving deep-learning models with reality checkscited by 1
  31. 2021Combining Transformers with Natural Language Explanationscited by 1
  32. 2022Interlock-Free Multi-Aspect Rationalization for Text Classificationcited by 1
  33. 2023Perturbation-based Self-supervised Attention for Attention Bias in Text Classificationcited by 1
  34. 2024Fighting Spurious Correlations in Text Classification via a Causal Learning Perspectivecited by 1
  35. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1
  36. 2025Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalizationcited by 1
  37. 2025Text Rationalization for Robust Causal Effect Estimationcited by 1
  38. 2024Interlocking-free Selective Rationalization Through Genetic-based Learningcited by 0

50 most cited of 54 All 54 (JSON)