Search Results for author:
Found 2 papers, 1 papers with code
Training and Evaluating a Jupyter Notebook Data Science Assistant
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).
DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons
The joint task of bug localization and program repair is an integral part of the software development process.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
