{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"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":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"1909.03496","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","created":"2019-09-08","cited_by_count":272},{"id":"1803.09473","title":"code2vec: Learning Distributed Representations of Code","created":"2018-03-26","cited_by_count":250},{"id":"1709.06182","title":"A Survey of Machine Learning for Big Code and Naturalness","created":"2017-09-18","cited_by_count":221},{"id":"1711.00740","title":"Learning to Represent Programs with Graphs","created":"2017-11-01","cited_by_count":220},{"id":"1808.01400","title":"code2seq: Generating Sequences from Structured Representations of Code","created":"2018-08-04","cited_by_count":179},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"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":"2203.07722","title":"ReACC: A Retrieval-Augmented Code Completion Framework","created":"2022-03-15","cited_by_count":119},{"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":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"1902.01954","title":"A Neural Model for Generating Natural Language Summaries of Program Subroutines","created":"2019-02-05","cited_by_count":77},{"id":"1805.11683","title":"DeepBugs: A Learning Approach to Name-based Bug Detection","created":"2018-04-30","cited_by_count":65},{"id":"1707.02275","title":"A parallel corpus of Python functions and documentation strings for automated code documentation and code generation","created":"2017-07-07","cited_by_count":57},{"id":"2003.07914","title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","created":"2020-03-17","cited_by_count":54},{"id":"1904.02660","title":"Recommendations for Datasets for Source Code Summarization","created":"2019-04-04","cited_by_count":46},{"id":"2005.02161","title":"LambdaNet: Probabilistic Type Inference using Graph Neural Networks","created":"2020-04-29","cited_by_count":44},{"id":"1512.06448","title":"SourcererCC: Scaling Code Clone Detection to Big Code","created":"2015-12-20","cited_by_count":40},{"id":"1904.01720","title":"Neural Program Repair by Jointly Learning to Localize and Repair","created":"2019-04-03","cited_by_count":40},{"id":"1905.13334","title":"How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Dataset","created":"2019-05-30","cited_by_count":36},{"id":"1803.09371","title":"StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow","created":"2018-03-26","cited_by_count":30},{"id":"2004.10657","title":"Typilus: Neural Type Hints","created":"2020-04-06","cited_by_count":29},{"id":"2111.03922","title":"Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs","created":"2021-11-06","cited_by_count":25},{"id":"2103.11599","title":"Project-Level Encoding for Neural Source Code Summarization of Subroutines","created":"2021-03-22","cited_by_count":24},{"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":"1807.03168","title":"NAPS: Natural Program Synthesis Dataset","created":"2018-07-06","cited_by_count":14},{"id":"2109.08780","title":"Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy","created":"2021-09-17","cited_by_count":14},{"id":"1905.11445","title":"COSET: A Benchmark for Evaluating Neural Program Embeddings","created":"2019-05-27","cited_by_count":10},{"id":"2104.04706","title":"ManyTypes4Py: A Benchmark Python Dataset for Machine Learning-based Type Inference","created":"2021-04-10","cited_by_count":9},{"id":"1802.07779","title":"Path-Based Function Embedding and its Application to Specification Mining","created":"2018-02-21","cited_by_count":8},{"id":"2010.16196","title":"World of Code: Enabling a Research Workflow for Mining and Analyzing the Universe of Open Source VCS data","created":"2020-10-30","cited_by_count":7},{"id":"2201.10705","title":"Learning to Recommend Method Names with Global Context","created":"2022-01-26","cited_by_count":6},{"id":"2103.00269","title":"A Context-based Automated Approach for Method Name Consistency Checking and Suggestion","created":"2021-02-27","cited_by_count":5},{"id":"2208.00203","title":"Adding Context to Source Code Representations for Deep Learning","created":"2022-07-30","cited_by_count":2},{"id":"1901.05392","title":"The Maven Dependency Graph: a Temporal Graph-based Representation of Maven Central","created":"2019-01-16","cited_by_count":1}],"next_cursor":null}