Rationalizing Neural Predictions
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Prediction without justification has limited applicability.As a remedy, we learn to extract pieces of input text as justifications -rationales -that are tailored to be short and coherent, yet sufficient for making the same prediction.Our approach combines two modular components, generator and encoder, which are trained to operate well together.The generator specifies a distribution over text fragments as candidate rationales and these are passed through the encoder for prediction.Rationales are never given during training.Instead, the model is regularized by desiderata for rationales.We evaluate the approach on multi-aspect sentiment analysis against manually annotated test cases.Our approach outperforms attention-based baseline by a significant margin.We also successfully illustrate the method on the question retrieval task. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“A lot of work has also been done on argumentation and dialog games [6, 11, 51, 53] but the focus in these areas is generally the logical structure of the framework to express and to relate arguments or the protocol to exchange arguments.”
From Beyond explainability: justifiability and contestability of algorithmic decision systems (2022) · cites this paper as [53]
Experimental — accuracy not yet measuredIn the citing paper
“This model can achieve competitive accuracy while having built-in interpretability because the prediction is made exclusively based on rationales.”
From Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation (2022) · cites this paper as [52]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016) · arXiv · doi:10.48550/arxiv.1607.01759 · Cited by 4,542
A Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1062 · Cited by 3,601 · cited 1×
“For instance, we could use a convolutional network (Kim, 2014; Kalchbrenner et al., 2014), deep averaging network (Iyyer et al.”
MethodA Neural Attention Model for Abstractive Sentence Summarization
Rush, A. M., Chopra, S., & Weston, J. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1044 · Cited by 2,656
Recurrent Models of Visual Attention
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 2,568 · cited 1×
“space of possible rationales in terms of their interaction with the encoder. We could also apply variance reduction techniques to increase stability of stochastic training (cf. (Weaver and Tao, 2001; Mnih et al., 2014; Ba et al., 2015; Xu et al., 2015)). 7 Acknowledgments We thank Prof. Julian McAuley for sharing the…”
MethodTeaching Machines to Read and Comprehend
Hermann, K. M., Kočiský, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., & Blunsom, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03340 · Cited by 2,521
Long Short-Term Memory-Networks for Machine Reading
Cheng, J., Dong, L., & Lapata, M. (2016) · arXiv · doi:10.48550/arxiv.1601.06733 · Cited by 1,198 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundLong Short-Term Memory-Networks for Machine Reading
Cheng, J., Dong, L., & Lapata, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1053 · Cited by 1,172 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundVisualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 1×
“Efforts in this area include analyzing and visualizing state activation (Hermans and Schrauwen, 2013; Karpathy et al., 2015; Li et al., 2016), learning sparse interpretable word vectors (Faruqui et al., 2015b), and linking word vectors to semantic lexicons or word properties (Faruqui et al., 2015a;…”
BackgroundMultiple Object Recognition with Visual Attention
Ba, J., Mnih, V., & Kavukcuoglu, K. (2014) · arXiv · doi:10.48550/arxiv.1412.7755 · Cited by 808 · cited 1×
“(Weaver and Tao, 2001; Mni et al., 2014; Ba et al., 2015; Xu et al., 2015)).”
Letham, B., Rudin, C., McCormick, T. H., & Madigan, D. (2015) · The Annals of Applied Statistics · doi:10.1214/15-aoas848 · Cited by 766 · cited 1×
“Developing sparse interpretable models holds considerably interest in the broader research community(Letham et al., 2015; Kim et al., 2015).”
BackgroundAsk, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
Xu, H., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_28 · Cited by 727 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundTraining and Analysing Deep Recurrent Neural Networks
Hermans, M., & Schrauwen, B. (2013) · neural information processing systems · Cited by 631
Visualizing and Understanding Neural Models in NLP
Li, J., Chen, X., Hovy, E., & Jurafsky, D. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1082 · Cited by 625 · cited 1×
“Efforts in this area include analyzing and visualizing state activation (Hermans and Schrauwen, 2013; Karpathy et al., 2015; Li et al., 2016), learning sparse interpretable word vectors (Faruqui et al., 2015b), and linking word vectors to semantic lexicons or word properties (Faruqui et al., 2015a;…”
BackgroundExtracting Tree-Structured Representations of Trained Networks
Craven, M. W., & SHAVLIK, J. W. (1995) · neural information processing systems · Cited by 602
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
Martins, A. F. T., & Astudillo, R. F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02068 · Cited by 431
A Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1404.2188 · Cited by 407 · cited 1×
“For instance, we could use a convolutional network (Kim, 2014; Kalchbrenner et al., 2014), deep averaging network (Iyyer et al.”
MethodUsing “annotator rationales” to improve machine learning for text categorization
Zaidan, O. F., Eisner, J. M., & Piatko, C. (2007) · Cited by 393
RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv044 · Cited by 317
ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
Chen, K., Wang, J., Chen, L.-C., Gao, H., Xu, W., & Nevatia, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05960 · Cited by 254 · cited 1×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundLearning Attitudes and Attributes from Multi-aspect Reviews
McAuley, J., Leskovec, J., & Jurafsky, D. (2012) · 2012 IEEE 12th International Conference on Data Mining · doi:10.1109/icdm.2012.110 · Cited by 245
Stacked Attention Networks for Image Question AnsweringPreprint
Yang, Z., He, X., Gao, J., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.02274 · Cited by 192 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundSparse Overcomplete Word Vector Representations
Faruqui, M., Tsvetkov, Y., Yogatama, D., Dyer, C., & Smith, N. A. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1144 · Cited by 157 · cited 1×
“…analyzing and visualizing state activation (Hermans and Schrauwen, 2013; Karpathy et al., 2015; Li et al., 2016), learning sparse interpretable word vectors (Faruqui et al., 2015b), and linking word vectors to semantic lexicons or word properties (Faruqui et al., 2015a; Herbelot and Vecchi, 2015).”
BackgroundThe Optimal Reward Baseline for Gradient-Based Reinforcement Learning
Weaver, L., & Tao, N. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.2315 · Cited by 144 · cited 1×
“(Weaver and Tao, 2001; Mni et al., 2014; Ba et al., 2015; Xu et al., 2015)).”
Semi-supervised Question Retrieval with Gated Convolutions
Lei, T., Joshi, H., Barzilay, R., Jaakkola, T., Tymoshenko, K., Moschitti, A., & Màrquez, L. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1153 · Cited by 126
Self-citationMind the Gap: a generative approach to interpretable feature selection and extraction
Kim, B., Shah, J., & Doshi‐Velez, F. (2015) · neural information processing systems · Cited by 122
Molding CNNs for text: non-linear, non-consecutive convolutions
Lei, T., Barzilay, R., & Jaakkola, T. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1180 · Cited by 121 · cited 4×
“We use the “one-versus-all” hinge loss (i.e. positive versus other negatives) for the encoder, similar to (Lei et al., 2015b).”
MethodInfluentialSelf-citationAsk, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question AnsweringPreprint
Xu, H. J., & Saenko, K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05234 · Cited by 104 · cited 2×
“Attention based models offer another lens to the inner workings of neural models (Bahdanau et al., 2015; Cheng et al., 2016; Martins and Astudillo, 2016; Chen et al., 2015; Xu and Saenko, 2015; Yang et al., 2015).”
BackgroundLearning Hybrid Representations to Retrieve Semantically Equivalent Questions
dos Santos, C., Barbosa, L., Bogdanova, D., & Zadrozny, B. (2015) · doi:10.3115/v1/p15-2114 · Cited by 95 · cited 1×
“Dataset For our second application, we use the real-world AskUbuntu 5 dataset used in recent work (dos Santos et al., 2015; Lei et al., 2015b).”
MethodRationale-Augmented Convolutional Neural Networks for Text ClassificationPreprint
Zhang, Y., Marshall, I. J., & Wallace, B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.04469 · Cited by 23 · cited 1×
“Finally, we contrast our work with rationale-based classification (Zaidan et al., 2007; Marshall et al., 2015; Zhang et al., 2016) which seek to improve prediction by relying on richer annotations in the form of human-provided rationales.”
Result
Research works printed but not linked: 7
- [6]6. Cicero dos Santos, Luciano Barbosa, Dasha Bogdanova, and Bianca Zadrozny. 2015. Learning hybrid rep- resentations to retrieve semantically equivalent ques- tions. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Lan- guage Processing (Volume 2: Short Papers), pages 694-699, Beijing, China, July. Association for Com- putational Linguistics.
- [7]7. Manaal Faruqui, Jesse Dodge, Sujay K. Jauhar, Chris Dyer, Eduard Hovy, and Noah A. Smith. 2015a. Retrofitting word vectors to semantic lexicons. In Pro- ceedings of NAACL.
- [9]9. Aurélie Herbelot and Eva Maria Vecchi. 2015. Build- ing a shared world: mapping distributional to model- theoretic semantic spaces. In Proceedings of the 2015 Conference on Empirical Methods in Natural Lan- guage Processing. Association for Computational Lin- guistics.
- [12]12. Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, and Hal Daumé III. 2015. Deep unordered compo- sition rivals syntactic methods for text classification. In Proceedings of the 53rd Annual Meeting of the As- sociation for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers).
- [17]17. Yoon Kim. 2014. Convolutional neural networks for sen- tence classification. In Proceedings of the Empiricial Methods in Natural Language Processing (EMNLP 2014).
- [27]27. Tim Rocktäschel, Edward Grefenstette, Karl Moritz Her- mann, Tomáš Kočiskỳ, and Phil Blunsom. 2016. Rea- soning about entailment with neural attention. In In- ternational Conference on Learning Representations.
- [29]29. Sebastian Thrun. 1995. Extracting rules from artifi- cial neural networks with distributed representations. In Advances in neural information processing systems (NIPS).
Cited by
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922
“In [43], an interpretability technique for neural networks operating in the natural language processing (NLP) domain was proposed.”
Metadata
- Authors
- Lei, T., Barzilay, R., & Jaakkola, T.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Pages
- 107-117
- OpenAlex
- W2440159969
- Cited by
- 777
- References
- 27
- Citations by year
- 2026: 27 · 2025: 33 · 2024: 39 · 2023: 88 · 2022: 92 · 2021: 138 · 2020: 126 · 2019: 101 · 2018: 78 · 2017: 39 · 2016: 4
- FWCI
- 39.87
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- explanation generation, question retrieval, model regularization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.