Patents by Inventor ALEXEY SVYATKOVSKIY

ALEXEY SVYATKOVSKIY has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • NEURAL CODE COMPLETION VIA RE-RANKING
    Publication number: 20210279042
    Abstract: A code completion system uses neural components to rank the unordered list of code completion candidates generated from an existing static analyzer. The candidates represent the next sequence of tokens likely to complete a partially-formed program element as a developer is typing in a software development tool. A re-ranking component generates a ranked order of the candidates based on a context embedding of the code context and candidate embeddings of the candidates, where both embeddings are based a common token encoding.
    Type: Application
    Filed: June 15, 2020
    Publication date: September 9, 2021
    Inventors: MILTIADIS ALLAMANIS, SHENGYU FU, XIAOYU LIU, NEELAKANTAN SUNDARESAN, ALEXEY SVYATKOVSKIY
  • DEEP LEARNING ENHANCED CODE COMPLETION SYSTEM
    Publication number: 20210271455
    Abstract: A code completion tool uses a deep learning model to predict the likelihood of a method completing a method invocation. In one aspect, the deep learning model is a LSTM trained on features that represent the syntactic context of a method invocation derived from an abstract tree representation of the code fragment.
    Type: Application
    Filed: April 18, 2021
    Publication date: September 2, 2021
    Inventors: ALEXEY SVYATKOVSKIY, SHENGYU FU, NEELAKANTAN SUNDARESAN, YING ZHAO
  • Deep learning enhanced code completion system
    Patent number: 10983761
    Abstract: A code completion tool uses a deep learning model to predict the likelihood of a method completing a method invocation. In one aspect, the deep learning model is a LSTM trained on features that represent the syntactic context of a method invocation derived from an abstract tree representation of the code fragment.
    Type: Grant
    Filed: April 8, 2019
    Date of Patent: April 20, 2021
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Alexey Svyatkovskiy, Shengyu Fu, Neelakantan Sundaresan, Ying Zhao
  • MULTI-LINGUAL LINE-OF-CODE COMPLETION SYSTEM
    Publication number: 20210034335
    Abstract: A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.
    Type: Application
    Filed: November 11, 2019
    Publication date: February 4, 2021
    Inventors: Alexey Svyatkovskiy, Shengyu Fu, Neelakantan Sundaresan, Shao Kun Deng
  • DEEP LEARNING ENHANCED CODE COMPLETION SYSTEM
    Publication number: 20200249918
    Abstract: A code completion tool uses a deep learning model to predict the likelihood of a method completing a method invocation. In one aspect, the deep learning model is a LSTM trained on features that represent the syntactic context of a method invocation derived from an abstract tree representation of the code fragment.
    Type: Application
    Filed: April 8, 2019
    Publication date: August 6, 2020
    Inventors: ALEXEY SVYATKOVSKIY, SHENGYU FU, NEELAKANTAN SUNDARESAN, YING ZHAO