Rationalizing Neural Predictions
Open accessThe DOI matches its Crossref record; 35 of the 35 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).”
BackgroundConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Show, 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
Research works printed but not linked: 6
- [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).
- [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
Items 701–800 of 900
What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
Mahmood, R., Peddinti, S. T., Ahmed, T., & Huang, D. Y. (2026) · Proceedings of the ACM on Networking · doi:10.1145/3808674 · Cited by 3
“All experiments are conducted on a single NVIDIA A100 GPU (80GB).”
Opinion Summarization and Search
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.010 · Cited by 2
Widener, D. V., Mazzuchi, T. A., & Sarkani, S. (2017) · Disaster Prevention and Management An International Journal · doi:10.1108/dpm-06-2017-0134 · Cited by 3
Stefchov, E., Angelova, G., & Nakov, P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99344-7_11 · Cited by 1
“, using clustering [12] and deep learning [5].”
BackgroundMethodInfluentialDocument Sentiment Classification
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.004 · Cited by 2
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.008 · Cited by 1
Aspect Sentiment Classification
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.006 · Cited by 1
Version space learning for verification on temporal differentials
Santolucito, M. (2017) · ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) · doi:10.1145/3092703.3098238 · Cited by 1
“Legibility is a difficult property to achieve in machine learning and an active area of research [8].”
BackgroundAnalysis of Implicit Conditions in Database Search Dialogues
Fukunaga, S.-Y., Nishikawa, H., Tokunaga, T., Yokono, H., & Takahashi, T. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/3ax3wut72unq · Cited by 1
“For this task, we plan to use the machine learning techniques which can provide the rationales for the output (Lei et al., 2016).”
MethodPolytopic Trees for Verification of Learning-Based Controllers
Sadraddini, S., Shen, S., & Bastani, O. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-28423-7_8 · Cited by 1
“A promising direction to resolve this issue is focusing on interpretable neural networks [3, 19], which are trained in a way that they are less fragile and typically have fewer and larger affine cells.”
BackgroundThe influence of financial practice in developing mathematical probability
Johnson, T. C. (2020) · Synthese · doi:10.1007/s11229-020-02636-w · Cited by 1
“This relates to questions about the deployment of Artificial Intelligence within an organisation and how to make AI more trustworthy (Lei et al. 2016; Tarafdar et al. 2017).”
BackgroundLiu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.008 · Cited by 1
TRIPLEx: Triple Extraction for Explanation
Setzu, M., Monreale, A., & Minervini, P. (2021) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi52975.2021.00015 · Cited by 4
Dimensions of Explanatory Value in NLP Models
van Deemter, K. (2023) · Computational Linguistics · doi:10.1162/coli_a_00480 · Cited by 6
“Suppose the model has terrible performance but admirable explainability, for instance via computer-generated “rationales” that highlight essay fragments that were particularly important for each classification decision (as in Lei, Barzilay, and Jaakola 2016, for example).”
MethodInterpreting Sentiment Composition with Latent Semantic Tree
Jiang, Z., Zhang, Y., Cao, L., Chen, J., Zhao, J., & Liu, K. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.471 · Cited by 1
“…to figure out which input feature, say word, has the most influence on the prediction, in the form of the salience score or rationale, and in both self and post-hoc settings (Li et al., 2016; Ribeiro et al., 2016; Kim et al., 2020; Lei et al., 2016; Bastings et al., 2019; De Cao et al., 2020).”
BackgroundAn Empirical Study on Model-Agnostic Techniques for Source Code-Based Defect Prediction
Zhu, Y., Gao, Y., & Yu, Q. (2023) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194023500572 · Cited by 1
Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing
Kur, J., Chen, J., & Huang, J. (2023) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00161 · Cited by 1
“Rationalization discussed in [6], [7] is a representative instance of XAI.”
BackgroundConditional Natural Language Inference
Kim, Y., Rahimi, R., & Allan, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.456 · Cited by 5
“A token being important to the model decision is justified by how it is connected (gradient or active weights) to the model decision (Gilpin et al., 2018) or how its existence (or removal) affects the model decision (Lei et al., 2016; DeYoung et al., 2020).”
BackgroundLiang, T., Mu, Y., Kim, S., Kuate, D. L. K., Lang, J., Vos, R. D., & Song, X. (2023) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-092-2_072 · Cited by 1
Adversarial Attack for Explanation Robustness of Rationalization Models
Zhang, Y., Kong, L., Wang, H., Li, R., Wang, J., Li, Y., & Liu, W. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240752 · Cited by 3
Tocchetti, A., Yang, J., & Brambilla, M. (2023) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha) · Cited by 1
Deep Reinforcement Learning in Natural Language Scenarios
He, J. (2017) · ResearchWorks at the University of Washington (University of Washington) · Cited by 1
Relating lexical and syntactic processes in language: Bridging research in humans and machines
Ettinger, A. (2018) · University Libraries (University of Maryland) · doi:10.13016/m2s756p4g · Cited by 2
Multi-Dimensional Explanation of ReviewsPreprint
Antognini, D., Musat, C., & Faltings, B. V. (2019) · arXiv (Cornell University) · Cited by 1
KnowBias: Detecting Political Polarity in Long Text ContentPreprint
Saligrama, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12230 · Cited by 1
“Previous work has filtered text in order to derive justifiable predictions (Lei, Barzilay, and Jaakkola 2016), but not for domain adaptation for our target problem.”
BackgroundWang, J., Sun, C., Li, S., Wang, J., Si, L., Zhang, M., Liu, X., & Zhou, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.09260 · Cited by 1
“We conduct our experiments on three public datasets on DASC, i.e., TripUser (Li et al., 2018), TripAdvisor (Wang et al., 2010) and BeerAdvo-cate (McAuley et al., 2012; Lei et al., 2016).”
MethodAdvanced Review Helpfulness Modeling
Du, J. (2020) · Victoria University Research Repository (Victoria University) · Cited by 1
Machine-annotated rationales: faithfully explaining machine learning models for text classification
Herrewijnen, E. (2020) · Utrecht University Repository (Utrecht University) · Cited by 1
Pattanayak, K., & Krishnamurthy, V. (2021) · arXiv (Cornell University) · Cited by 1
Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse CommunicationPreprint
Martins, A. F. T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00755 · Cited by 1
“Existing approaches rely on score function estimation (Lei et al., 2016), continuous relaxations combined with the reparametrization trick (Bastings et al., 2019), and sparse relaxations (Treviso and Martins, 2020).”
BackgroundMethodModeling text embedded information cascades
Xu, S. (2019) · Digital Repository Service (Northeastern University) · doi:10.17760/d20328884 · Cited by 1
From medical imaging to explainable artificial intelligence
Tjoa, E. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/164493 · Cited by 1
Dong, J., Chen, S., & Labi, S. (2023) · Purdue e-Pubs (Purdue University System) · doi:10.5703/1288284317701 · Cited by 2
Predicting Startup Funding Momentum with Collective IntelligencePreprint
Kehler, T., Liu, F., Olfat, M., & Sinha, S. (2024) · doi:10.31219/osf.io/k6wq5 · Cited by 1
Aligning Human and Machine Attention for Enhanced Supervised LearningPreprint
Chriqui, A., Yahav, I., Te’eni, D., & Abbasi, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.06811 · Cited by 1
X-Troll: eXplainable Detection of State-Sponsored Information Operations AgentsPreprint
Tian, L., Zhang, X., Kim, M., Biggs, J., & Rizoiu, M.-A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.16021 · Cited by 1
“Rationalization, in particular, involves identifying input phrases sufficient to predict the desired outcome [24, 27].”
Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language ModelsPreprint
Deiseroth, B., Höth, M. H., Kersting, K., & Parcalabescu, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.11614 · Cited by 1
“Most relevant to our work are erasure and rationale methods that remove or select minimal subsets [17, 16] as well as counterfactual editing methods [26, 38], which alter inputs and observe behavioral changes.”
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical JudgmentsPreprint
Machidon, O. M., Machidon, A. L., Strahovnik, V., Strahovnik, M. C., Miklavčič, J., & Robnik‐Šikonja, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.12368 · Cited by 1
Learning to Give Checkable Answers with Prover-Verifier Games
Anil, C., Zhang, G., Wu, Y., & Grosse, R. (2021) · arXiv · doi:10.48550/arxiv.2108.12099
“With text applications in mind, [20] propose a two player, collaborative game where a generator network selects relevant features from the input text, and a predictor network does classification using those features.”
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.007
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.014
Analysis of Debates and Comments
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.011
Analysis of Comparative Opinions
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.009
Detecting Fake or Deceptive Opinions
Liu, B. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781139084789.013 · Cited by 1
Nilforoshan, H., Sands, J. K., Lin, K., Khanna, R., & Wu, E. (2017) · arXiv (Cornell University)
Computational Natural Language Inference: Robust and Interpretable Question Answering
Sharp, R. (2017) · UA Campus Repository (The University of Arizona)
Research of the methods of the analysis of reviews about the goods of electronics shops
Vechur, O., & Spodarets, O. (2018) · ScienceRise · doi:10.15587/2313-8416.2018.135069
Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences
Hsu, S. T., Chaudhary, M. S., & Samatova, N. F. (2018) · International Conference on Computational Linguistics
Interpretation of Implicit Conditions in Database Search Dialogues
Fukunaga, S.-Y., Nishikawa, H., Tokunaga, T., Yokono, H., & Takahashi, T. (2019) · Journal of Natural Language Processing · doi:10.5715/jnlp.26.121
“We use the cross-entropy instead of the square error for the encoder loss function, as our task is the binary classification while Lei et al. (2016)’s is the regression.”
MethodInfluentialTraining Machine Learning Models by Regularizing their ExplanationsPreprint
Ross, A. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00869
“This approach to explanations can be domain- and model-specific (e.g. “annotator rationales” used to explain text classifications by Li et al. (2016); Lei et al. (2016); Zhang et al. (2016)).”
BackgroundWang, W. (2018) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/75872
“They include recursive neural networks [26], recurrent neural networks [107, 96, 132], attentions [109, 70, 15] and auto-encoders [60].”
Rationalizing Translation Elongation by Reinforcement LearningPreprint
Hu, H., Liu, X., Xiao, A., Li, Y., Zhang, C., Jiang, T., Zhao, D., Song, S., & Zeng, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3543842
Evaluating style transfer in natural language
Matthews, N. E. (2018) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Hierarchical Models of Biological Systems
Yu, M. (2017) · eScholarship (California Digital Library)
Question answering with textual sequence matching
Wang, S. (2019) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University)
Learning Patient Engagement in Care Management: Performance vs. InterpretabilityPreprint
Das, S., Maduri, C., Chen, C.-H., & Hsueh, P.-Y. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.08339
Theopolis Monk: Envisioning a Future of A.I. Public Service
Hawley, S. H. (2019) · Springer eBooks · doi:10.1007/978-3-030-16920-6_14
Robot Consciousness: Physics and Metaphysics Here and AbroadPreprint
Ripley, S. B. (2020) · doi:10.36227/techrxiv.12902687.v1
Generating rationale for molecular prediction using reinforcement learning
Chen, B. (2019) · DSpace@MIT (Massachusetts Institute of Technology)
Learning structured task related abstractions
Penkov, S. (2019) · ERA · Cited by 1
A Joint Neural Model for Patent Classification and Rationale Identification
Koreeda, Y., Mase, H., & Yanai, K. (2019) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.f-ic1
Interpretable deep learning for natural language processing
Murdoch, W. J. (2019) · eScholarship (California Digital Library) · Cited by 1
Robust Text Classifier on Test-Time BudgetsPreprint
Parvez, R., Bolukbasi, T., Chang, K.-W., & Saligrama, V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08270 · Cited by 1
“We extend the parameter controlled joint training of (Lei, Barzilay, and Jaakkola 2016) for cross entropy loss function in order to incorporate any state-of-art classifier .”
BackgroundMethodResultInfluentialLearning Natural Language Interfaces using Deep Neural Networks
Gür, İ. (2019) · eScholarship (California Digital Library)
Behavioral Facilitation Tweets with Basis Extraction
Yoneda, Y., Suzuki, Y., & Nadamoto, A. (2019) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2019.00070
“Lei et al.[2] propose a method to extract the rationale of evaluation of each evaluation item from product reviews.”
MethodModeling text embedded information cascades
Xu, S. (2019)
Outline Extraction with Question-Specific Memory Cells
Yang, J., Cui, H., Li, S., Gao, S., Guo, J. H., & Lu, Z. (2020) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3377707
“• RCNN [23]: This is proposed by Lei et al. to extract pieces of text as rationales to explain prediction scores of five aspects.”
BackgroundMethodInfluentialKnowBias: Detecting Political Polarity in Long Text Content (Student Abstract)
Saligrama, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i10.7224
Automatic Approval of Online Comments with Multiple-Encoder Networks
Dang, V. M. H. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-6168-9_20
Towards a Framework for Challenging ML-Based Decisions
Henin, C., & Métayer, D. L. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-91779-1_10
“In other papers [13], justifications are seen as ways to make understandable the inner operations of a complex system (in a white-box setting).”
BackgroundShi, T., Wang, P., & Reddy, C. K. A. (2020) · arXiv (Cornell University)
Determine and explain confidence in predicting violations on inland ships in the Netherlands
de Bakker, P. I. W. (2020) · Research Repository (Delft University of Technology)
DoLFIn: Distributions over Latent Features for Interpretability
Le, P., & Zuidema, W. H. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.127
Training with Adversaries to Improve Faithfulness of Attention in Neural Machine Translation
Moradi, P., Kambhatla, N., & Sarkar, A. (2020) · Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing: Student Research Workshop (AACL-IJCNLP SRW) · doi:10.18653/v1/2020.aacl-srw.14 · Cited by 1
“[33] propose a model in which first a rationale is selected from the input and then is further used for prediction.”
BackgroundRossini, D., Croce, D., & Basili, R. (2019) · Italian Journal of Computational Linguistics · doi:10.4000/ijcol.453
Oro, E., Ruffolo, M., & Visalli, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-71158-0_21
An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment AnalysisPreprint
Shi, T., Wang, P., & Reddy, C. K. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09112
“TripAdvisor-R [38], TripAdvisor-U [13] and BeerAdvocate-R [12, 38] use the original rating scores as sentiment class labels.”
MethodLearnt Sparsity for Effective and Interpretable Document Ranking.Preprint
Leonhardt, J., Rudra, K., & Anand, A. (2021) · arXiv (Cornell University)
Zhang, H. (2021) · D-Scholarship@Pitt (University of Pittsburgh)
Novel Algorithms for Understanding Online Reviews
Shi, T. (2021) · VTechWorks (Virginia Tech)
A Framework for Rationale Extraction for Deep QA modelsPreprint
Ramnath, S., Nema, P., Sahni, D., & Khapra, M. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.04620
“The others (Lei et al., 2016) introduce and train a rationale generation/extraction component as a part of the model itself.”
BackgroundLeveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial SpacesPreprint
Struminsky, K., Gadetsky, A., Rakitin, D., Karpushkin, D., & Vetrov, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15072
“In particular, we took its decorrelated subset along with the pretrained embeddings from [27].”
MethodContrapositive Local Class Inference
Kashefi, O., & Hwa, R. (2021) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2021.wnut-1.41
“However, some studies have tried to develop systems for automatic extraction of the rationales (Lei et al., 2016; Ehsan et al., 2018) as the smaller text span that could replace the whole greater-context, while keeping the global-prediction intact: Alternatively, the contrapositive inference…”
BackgroundMethodSelf-explanatory neural models, part 2
Rguibi, Z., Hajami, A., & Zitouni, D. (2021) · MOL2NET International Conference on Multidisciplinary Sciences (MOL2NET) · doi:10.3390/mol2net-07-11237
Explaining Deep Neural Networks in medical imaging context.
Rguibi, Z., Hajami, A., & Zitouni, D. (2021) · MOL2NET International Conference on Multidisciplinary Sciences (MOL2NET) · doi:10.3390/mol2net-07-11235
“[4] introduced a self-explanatory neural network where the explanation generator selects a subset of the input features, which are then exclusively passed to the predictor that provides the final answer based solely on the selected features.”
BackgroundTowards a framework for challenging ML-based decisions
Henin, C., & Métayer, D. L. (2020) · HAL · Cited by 1
Opinion mining on digital media data: advancing state-of-the-art methods with deep learning
Quan, W., & Hu, X. T. (2020) · iDEA - Drexel University Institutional Repository · doi:10.17918/00000233
Analysis of Debates and Comments
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.011
Analysis of Comparative Opinions
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.009
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.012
Aspect Sentiment Classification
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.006
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.017
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.014
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.001
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.015
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.016
Opinion Summarization and Search
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.010 · Cited by 1
Document Sentiment Classification
Liu, B. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108639286.004
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.