Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Alexey Svyatkovskiy

Alexey Svyatkovskiy

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation


Feb 09, 2021
Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, Shujie Liu

Figure 1 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 2 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 3 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 4 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

  Access Paper or Ask Questions

PyMT5: multi-mode translation of natural language and Python code with transformers


Oct 07, 2020
Colin B. Clement, Dawn Drain, Jonathan Timcheck, Alexey Svyatkovskiy, Neel Sundaresan

Figure 1 for PyMT5: multi-mode translation of natural language and Python code with transformers
Figure 2 for PyMT5: multi-mode translation of natural language and Python code with transformers
Figure 3 for PyMT5: multi-mode translation of natural language and Python code with transformers
Figure 4 for PyMT5: multi-mode translation of natural language and Python code with transformers
* 14 pages, 7 figures, 5 tables, EMNLP 2020 camera ready version 
  Access Paper or Ask Questions

GraphCodeBERT: Pre-training Code Representations with Data Flow


Sep 29, 2020
Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, Ming Zhou

Figure 1 for GraphCodeBERT: Pre-training Code Representations with Data Flow
Figure 2 for GraphCodeBERT: Pre-training Code Representations with Data Flow
Figure 3 for GraphCodeBERT: Pre-training Code Representations with Data Flow
Figure 4 for GraphCodeBERT: Pre-training Code Representations with Data Flow

  Access Paper or Ask Questions

Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers


Sep 11, 2020
Michele Tufano, Dawn Drain, Alexey Svyatkovskiy, Neel Sundaresan

Figure 1 for Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers
Figure 2 for Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers
Figure 3 for Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers
Figure 4 for Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers

  Access Paper or Ask Questions

Unit Test Case Generation with Transformers


Sep 11, 2020
Michele Tufano, Dawn Drain, Alexey Svyatkovskiy, Shao Kun Deng, Neel Sundaresan

Figure 1 for Unit Test Case Generation with Transformers
Figure 2 for Unit Test Case Generation with Transformers
Figure 3 for Unit Test Case Generation with Transformers
Figure 4 for Unit Test Case Generation with Transformers

  Access Paper or Ask Questions

IntelliCode Compose: Code Generation Using Transformer


May 16, 2020
Alexey Svyatkovskiy, Shao Kun Deng, Shengyu Fu, Neel Sundaresan

Figure 1 for IntelliCode Compose: Code Generation Using Transformer
Figure 2 for IntelliCode Compose: Code Generation Using Transformer
Figure 3 for IntelliCode Compose: Code Generation Using Transformer
Figure 4 for IntelliCode Compose: Code Generation Using Transformer
* 15 pages, 6 figures 
  Access Paper or Ask Questions

Fast and Memory-Efficient Neural Code Completion


Apr 29, 2020
Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi, Maik Riechert, Juliana Franco, Miltiadis Allamanis

Figure 1 for Fast and Memory-Efficient Neural Code Completion
Figure 2 for Fast and Memory-Efficient Neural Code Completion
Figure 3 for Fast and Memory-Efficient Neural Code Completion
Figure 4 for Fast and Memory-Efficient Neural Code Completion

  Access Paper or Ask Questions

Large-scale text processing pipeline with Apache Spark


Dec 02, 2019
Alexey Svyatkovskiy, Kosuke Imai, Mary Kroeger, Yuki Shiraito

Figure 1 for Large-scale text processing pipeline with Apache Spark
Figure 2 for Large-scale text processing pipeline with Apache Spark
Figure 3 for Large-scale text processing pipeline with Apache Spark
Figure 4 for Large-scale text processing pipeline with Apache Spark
* Published in Proceedings of Big NLP workshop at the IEEE Big Data Conference 2016 
  Access Paper or Ask Questions

Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters


Nov 30, 2019
Alexey Svyatkovskiy, Julian Kates-Harbeck, William Tang

Figure 1 for Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters
Figure 2 for Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters
Figure 3 for Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters
Figure 4 for Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters
* Published in Proceedings of the Machine Learning on HPC Environments (MLHPC) at the Supercomputing conference 2017 
  Access Paper or Ask Questions

Pythia: AI-assisted Code Completion System


Nov 29, 2019
Alexey Svyatkovskiy, Ying Zhao, Shengyu Fu, Neel Sundaresan

Figure 1 for Pythia: AI-assisted Code Completion System
Figure 2 for Pythia: AI-assisted Code Completion System
Figure 3 for Pythia: AI-assisted Code Completion System
Figure 4 for Pythia: AI-assisted Code Completion System
* Published in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD '19) 
  Access Paper or Ask Questions