no code implementations • 27 Jun 2022 • Spandan Garg, Roshanak Zilouchian Moghaddam, Colin B. Clement, Neel Sundaresan, Chen Wu
Additionally, we evaluate DeepPERF on 50 open source C# repositories on GitHub using both benchmark and unit tests and find that our model is able to suggest valid performance improvements that can improve both CPU usage and Memory allocations.
no code implementations • 27 Apr 2022 • Roshanak Zilouchian Moghaddam, Spandan Garg, Colin B. Clement, Yevhen Mohylevskyy, Neel Sundaresan
Continuous evolution in modern software often causes documentation, tutorials, and examples to be out of sync with changing interfaces and frameworks.
1 code implementation • 30 Jan 2022 • Shubham Chandel, Colin B. Clement, Guillermo Serrato, Neel Sundaresan
We study the feasibility of a Data Science assistant powered by a sequence-to-sequence transformer by training a new model JuPyT5 on all publicly available Jupyter Notebook GitHub repositories and developing a new metric: Data Science Problems (DSP).
no code implementations • EMNLP 2021 • Colin B. Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy
While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window.
no code implementations • 6 Aug 2021 • Colin B. Clement, Chen Wu, Dawn Drain, Neel Sundaresan
Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks.
no code implementations • 19 May 2021 • Dawn Drain, Colin B. Clement, Guillermo Serrato, Neel Sundaresan
The joint task of bug localization and program repair is an integral part of the software development process.
no code implementations • EMNLP 2020 • Colin B. Clement, Dawn Drain, Jonathan Timcheck, Alexey Svyatkovskiy, Neel Sundaresan
Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding.
1 code implementation • 30 Apr 2019 • Colin B. Clement, Matthew Bierbaum, Kevin P. O'Keeffe, Alexander A. Alemi
We use this pipeline to extract and analyze a 6. 7 million edge citation graph, with an 11 billion word corpus of full-text research articles.