{"list":"other","total":56,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"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":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"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":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"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":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"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":"1802.03691","title":"Tree-to-tree Neural Networks for Program Translation","created":"2018-02-11","cited_by_count":93},{"id":"1602.03001","title":"A Convolutional Attention Network for Extreme Summarization of Source Code","created":"2016-02-09","cited_by_count":91},{"id":"2004.02843","title":"Improved Code Summarization via a Graph Neural Network","created":"2020-04-06","cited_by_count":79},{"id":"1902.01954","title":"A Neural Model for Generating Natural Language Summaries of Program Subroutines","created":"2019-02-05","cited_by_count":77},{"id":"2007.04973","title":"Contrastive Code Representation Learning","created":"2020-07-09","cited_by_count":76},{"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":"2002.08653","title":"Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree","created":"2020-02-20","cited_by_count":69},{"id":"2102.07492","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","created":"2021-02-15","cited_by_count":68},{"id":"1805.11683","title":"DeepBugs: A Learning Approach to Name-based Bug Detection","created":"2018-04-30","cited_by_count":65},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2103.11318","title":"Language-Agnostic Representation Learning of Source Code from Structure and Context","created":"2021-03-21","cited_by_count":63},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63},{"id":"2105.08645","title":"CoTexT: Multi-task Learning with Code-Text Transformer","created":"2021-05-18","cited_by_count":61},{"id":"2012.14631","title":"Multi-task Learning based Pre-trained Language Model for Code Completion","created":"2020-12-29","cited_by_count":58},{"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":"1901.09102","title":"On Learning Meaningful Code Changes via Neural Machine Translation","created":"2019-01-25","cited_by_count":50},{"id":"2002.05800","title":"On Learning Meaningful Assert Statements for Unit Test Cases","created":"2020-02-13","cited_by_count":42},{"id":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41},{"id":"1904.01720","title":"Neural Program Repair by Jointly Learning to Localize and Repair","created":"2019-04-03","cited_by_count":40},{"id":"2201.01549","title":"SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations","created":"2022-01-05","cited_by_count":36},{"id":"2004.04881","title":"Improved Automatic Summarization of Subroutines via Attention to File Context","created":"2020-04-10","cited_by_count":34},{"id":"2006.12641","title":"Exploring Software Naturalness through Neural Language Models","created":"2020-06-22","cited_by_count":32},{"id":"2104.08006","title":"ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation","created":"2021-04-16","cited_by_count":31},{"id":"2012.14116","title":"Syntax-Enhanced Pre-trained Model","created":"2020-12-28","cited_by_count":30},{"id":"1906.08094","title":"Automatic Source Code Summarization with Extended Tree-LSTM","created":"2019-06-19","cited_by_count":28},{"id":"2105.04297","title":"How could Neural Networks understand Programs?","created":"2021-05-10","cited_by_count":26},{"id":"2104.07896","title":"Generating Bug-Fixes Using Pretrained Transformers","created":"2021-04-16","cited_by_count":18},{"id":"1904.09086","title":"Learning Programmatic Idioms for Scalable Semantic Parsing","created":"2019-04-19","cited_by_count":17},{"id":"2004.13214","title":"SCELMo: Source Code Embeddings from Language Models","created":"2020-04-28","cited_by_count":16},{"id":"1810.10641","title":"Predicting the Semantic Textual Similarity with Siamese CNN and LSTM","created":"2018-10-24","cited_by_count":14},{"id":"2006.04771","title":"Copy that! Editing Sequences by Copying Spans","created":"2020-06-08","cited_by_count":13},{"id":"2106.01367","title":"On using distributed representations of source code for the detection of C security vulnerabilities","created":"2021-06-01","cited_by_count":10},{"id":"2006.05265","title":"MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure","created":"2020-06-05","cited_by_count":6},{"id":"2110.10404","title":"JavaBERT: Training a transformer-based model for the Java programming language","created":"2021-10-20","cited_by_count":5}],"next_cursor":null}