Papers by Alexey Svyatkovskiy

4 papers
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy (2021.emnlp-main)

Copied to clipboard

Challenge: Statistical language modeling and translation with transformers have found many successful applications in program understanding and generation tasks.
Approach: They propose an architecture-independent approach for leveraging syntactic hierarchies of source code . they use syntax trees to extract syntak hierarchical structures and integrate them into context window .
Outcome: The proposed approach achieves state-of-the-art in code completion and summarization for Python in the CodeXGLUE benchmark.
ReACC: A Retrieval-Augmented Code Completion Framework (2022.acl-long)

Copied to clipboard

Challenge: Recent work has shown that statistical language modeling with transformers can greatly improve the performance in code completion tasks.
Approach: They propose a retrieval-augmented code completion framework that combines a source code retriever and an auto-regressive language model for programming language.
Outcome: The proposed framework achieves state-of-the-art on CodeXGLUE benchmark.
Code Execution with Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained code intelligence models ignore the execution trace and only rely on source code and syntactic structures to understand code execution.
Approach: They develop a mutation-based data augmentation technique to create a Python dataset and task for code execution that challenges existing models.
Outcome: The proposed model outperforms existing models on code execution and shows its potential for zero-shot code-to-code search and text-to code generation.
PyMT5: multi-mode translation of natural language and Python code with transformers (2020.emnlp-main)

Copied to clipboard

Challenge: Using Python method text-to-text transfer transformers, developers can easily model source code and natural language.
Approach: They propose a Python method text-to-text transfer transformer that can translate between all pairs of Python method feature combinations.
Outcome: The proposed model outperforms similar-sized auto-regressive language models on a large-scale parallel corpus of 26 million methods and 7.7 million method-docstring pairs on the CodeSearchNet test set.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations