{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1711.00740","title":"Learning to Represent Programs with Graphs","created":"2017-11-01","cited_by_count":220},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1901.01808","title":"SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair","created":"2018-12-24","cited_by_count":145},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2010.09337","title":"Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges","created":"2020-10-19","cited_by_count":120},{"id":"1805.04623","title":"Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context","created":"2018-05-12","cited_by_count":113},{"id":"1812.08693","title":"An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation","created":"2018-12-20","cited_by_count":108},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77},{"id":"1910.04210","title":"Perturbation Sensitivity Analysis to Detect Unintended Model Biases","created":"2019-10-09","cited_by_count":74},{"id":"2102.02017","title":"Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks","created":"2021-02-03","cited_by_count":70},{"id":"2003.07914","title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","created":"2020-03-17","cited_by_count":54},{"id":"2101.02518","title":"Towards Automating Code Review Activities","created":"2021-01-07","cited_by_count":54},{"id":"1901.09102","title":"On Learning Meaningful Code Changes via Neural Machine Translation","created":"2019-01-25","cited_by_count":50},{"id":"2008.01566","title":"On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations","created":"2020-07-31","cited_by_count":44},{"id":"2002.05800","title":"On Learning Meaningful Assert Statements for Unit Test Cases","created":"2020-02-13","cited_by_count":42},{"id":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40},{"id":"1506.01159","title":"On the \"Naturalness\" of Buggy Code","created":"2015-06-03","cited_by_count":35},{"id":"2009.06520","title":"A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research","created":"2020-09-14","cited_by_count":35},{"id":"1707.04742","title":"Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities","created":"2017-07-15","cited_by_count":26},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25},{"id":"2103.07115","title":"An Empirical Study on the Usage of BERT Models for Code Completion","created":"2021-03-12","cited_by_count":22},{"id":"2108.01585","title":"An Empirical Study on the Usage of Transformer Models for Code Completion","created":"2021-08-03","cited_by_count":22},{"id":"2108.13518","title":"DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions","created":"2021-08-27","cited_by_count":20},{"id":"2201.12046","title":"TSSB-3M: Mining single statement bugs at massive scale","created":"2022-01-28","cited_by_count":14},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14},{"id":"1812.10772","title":"Learning How to Mutate Source Code from Bug-Fixes","created":"2018-12-27","cited_by_count":13},{"id":"1903.05734","title":"Maybe Deep Neural Networks are the Best Choice for Modeling Source Code","created":"2019-03-13","cited_by_count":5},{"id":"1910.05493","title":"Deep Transfer Learning for Source Code Modeling","created":"2019-10-12","cited_by_count":4}],"next_cursor":null}