{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"2010.05607","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","created":"2020-10-12","cited_by_count":122},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2106.01798","title":"Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions","created":"2021-06-03","cited_by_count":98},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"2005.02439","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2020-05-05","cited_by_count":84},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"1906.03538","title":"Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims","created":"2019-06-08","cited_by_count":74},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"1906.08286","title":"Incorporating Priors with Feature Attribution on Text Classification","created":"2019-06-19","cited_by_count":68},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68},{"id":"1904.01606","title":"Inferring Which Medical Treatments Work from Reports of Clinical Trials","created":"2019-04-02","cited_by_count":64},{"id":"1412.6815","title":"Extraction of Salient Sentences from Labelled Documents","created":"2014-12-21","cited_by_count":50},{"id":"2010.12512","title":"Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification","created":"2020-10-23","cited_by_count":40},{"id":"1605.04469","title":"Rationale-Augmented Convolutional Neural Networks for Text Classification","created":"2016-05-14","cited_by_count":39},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36},{"id":"1802.04302","title":"Evaluating Compositionality in Sentence Embeddings","created":"2018-02-12","cited_by_count":35},{"id":"1905.13714","title":"Do Human Rationales Improve Machine Explanations?","created":"2019-05-31","cited_by_count":33},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32},{"id":"2010.08580","title":"Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets","created":"2020-10-16","cited_by_count":31},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31},{"id":"2004.07493","title":"TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition","created":"2020-04-16","cited_by_count":30},{"id":"1902.08649","title":"Saliency Learning: Teaching the Model Where to Pay Attention","created":"2019-02-22","cited_by_count":23},{"id":"2012.15482","title":"FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation","created":"2020-12-31","cited_by_count":21},{"id":"2109.08259","title":"Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU","created":"2021-09-17","cited_by_count":13},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9},{"id":"2106.01809","title":"Exploring Distantly-Labeled Rationales in Neural Network Models","created":"2021-06-03","cited_by_count":8},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7}],"next_cursor":null}