{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"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":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1808.09031","title":"Targeted Syntactic Evaluation of Language Models","created":"2018-08-27","cited_by_count":242},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"id":"1901.05287","title":"Assessing BERT's Syntactic Abilities","created":"2019-01-16","cited_by_count":192},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177},{"id":"2005.03692","title":"A Systematic Assessment of Syntactic Generalization in Neural Language Models","created":"2020-05-07","cited_by_count":165},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2009.13295","title":"A Diagnostic Study of Explainability Techniques for Text Classification","created":"2020-09-25","cited_by_count":159},{"id":"2005.00719","title":"Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?","created":"2020-05-02","cited_by_count":151},{"id":"1903.03260","title":"Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State","created":"2019-03-08","cited_by_count":138},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1602.07776","title":"Recurrent Neural Network Grammars","created":"2016-02-25","cited_by_count":109},{"id":"2004.10827","title":"Syntactic Structure from Deep Learning","created":"2020-04-22","cited_by_count":99},{"id":"1911.12246","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","created":"2019-11-27","cited_by_count":88},{"id":"1809.00042","title":"What do RNN Language Models Learn about Filler-Gap Dependencies?","created":"2018-08-31","cited_by_count":86},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"2012.15180","title":"Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?","created":"2020-12-30","cited_by_count":73},{"id":"2101.00010","title":"UnNatural Language Inference","created":"2020-12-30","cited_by_count":69},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62},{"id":"1904.00157","title":"Linguistic generalization and compositionality in modern artificial neural networks","created":"2019-03-30","cited_by_count":58},{"id":"2010.02180","title":"Pareto Probing: Trading Off Accuracy for Complexity","created":"2020-10-05","cited_by_count":55},{"id":"1901.04587","title":"Human few-shot learning of compositional instructions","created":"2019-01-14","cited_by_count":47},{"id":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44},{"id":"2106.08694","title":"On the proper role of linguistically-oriented deep net analysis in linguistic theorizing","created":"2021-06-16","cited_by_count":43},{"id":"2104.09635","title":"Refining Targeted Syntactic Evaluation of Language Models","created":"2021-04-19","cited_by_count":41},{"id":"2005.01641","title":"A Tale of a Probe and a Parser","created":"2020-05-04","cited_by_count":40},{"id":"1808.10627","title":"Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items","created":"2018-08-31","cited_by_count":36},{"id":"2008.06788","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","created":"2020-08-15","cited_by_count":34},{"id":"2004.14096","title":"Do Neural Language Models Show Preferences for Syntactic Formalisms?","created":"2020-04-29","cited_by_count":30},{"id":"1904.11829","title":"Evaluating Recurrent Neural Network Explanations","created":"2019-04-26","cited_by_count":29},{"id":"2005.13482","title":"Syntactic Structure Distillation Pretraining For Bidirectional Encoders","created":"2020-05-27","cited_by_count":18},{"id":"2012.05395","title":"Infusing Finetuning with Semantic Dependencies","created":"2020-12-10","cited_by_count":18},{"id":"1809.04022","title":"Can LSTM Learn to Capture Agreement? The Case of Basque","created":"2018-09-11","cited_by_count":17},{"id":"2107.13955","title":"Local Structure Matters Most: Perturbation Study in NLU","created":"2021-07-29","cited_by_count":10},{"id":"2101.11492","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","created":"2021-01-27","cited_by_count":6},{"id":"1908.11047","title":"Shallow Syntax in Deep Water","created":"2019-08-29","cited_by_count":3}],"next_cursor":null}