no code implementations • 23 Aug 2023 • Daniel Rodriguez-Cardenas, David N. Palacio, Dipin Khati, Henry Burke, Denys Poshyvanyk
We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods.
no code implementations • 7 Aug 2023 • David N Palacio, Alejandro Velasco, Daniel Rodriguez-Cardenas, Kevin Moran, Denys Poshyvanyk
To this end, this paper introduces ASTxplainer, an explainability method specific to LLMs for code that enables both new methods for LLM evaluation and visualizations of LLM predictions that aid end-users in understanding model predictions.
no code implementations • 7 Feb 2023 • David N. Palacio, Alejandro Velasco, Nathan Cooper, Alvaro Rodriguez, Kevin Moran, Denys Poshyvanyk
To demonstrate the practical benefit of $do_{code}$, we illustrate the insights that our framework can provide by performing a case study on two popular deep learning architectures and ten NCMs.
no code implementations • 3 Jan 2023 • Kevin Moran, Ali Yachnes, George Purnell, Junayed Mahmud, Michele Tufano, Carlos Bernal-Cárdenas, Denys Poshyvanyk, Zach H'Doubler
This paper offers one of the first comprehensive empirical investigations into the connection between GUIs and functional, natural language descriptions of software.
1 code implementation • 22 Jan 2021 • Nathan Cooper, Carlos Bernal-Cárdenas, Oscar Chaparro, Kevin Moran, Denys Poshyvanyk
Given the importance of visual information to the process of identifying and understanding such bugs, users are increasingly making use of screenshots and screen-recordings as a means to report issues to developers.
Optical Character Recognition Optical Character Recognition (OCR) +2
1 code implementation • 17 Sep 2020 • Prem Devanbu, Matthew Dwyer, Sebastian Elbaum, Michael Lowry, Kevin Moran, Denys Poshyvanyk, Baishakhi Ray, Rishabh Singh, Xiangyu Zhang
The intent of this report is to serve as a potential roadmap to guide future work that sits at the intersection of SE & DL.
no code implementations • 14 Sep 2020 • Cody Watson, Nathan Cooper, David Nader Palacio, Kevin Moran, Denys Poshyvanyk
An increasingly popular set of techniques adopted by software engineering (SE) researchers to automate development tasks are those rooted in the concept of Deep Learning (DL).
no code implementations • 18 May 2020 • Kevin Moran, David N. Palacio, Carlos Bernal-Cárdenas, Daniel McCrystal, Denys Poshyvanyk, Chris Shenefiel, Jeff Johnson
To this end, we design and implement a HierarchiCal PrObabilistic Model for SoftwarE Traceability (Comet) that is able to infer candidate trace links.
no code implementations • 18 May 2020 • Carlos Bernal-Cárdenas, Nathan Cooper, Kevin Moran, Oscar Chaparro, Andrian Marcus, Denys Poshyvanyk
In light of unique mobile development constraints, including swift release cycles and rapidly evolving platforms, automated techniques for analyzing all types of rich software artifacts provide benefit to mobile developers.
no code implementations • 12 Feb 2020 • Michele Tufano, Jason Kimko, Shiya Wang, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Denys Poshyvanyk
To this aim, two characteristics of mutation testing frameworks are of paramount importance: (i) they should generate mutants that are representative of real faults; and (ii) they should provide a complete tool chain able to automatically generate, inject, and test the mutants.
no code implementations • 25 Jan 2019 • Michele Tufano, Jevgenija Pantiuchina, Cody Watson, Gabriele Bavota, Denys Poshyvanyk
We show that, when applied in a narrow enough context (i. e., small/medium-sized pairs of methods before/after the pull request changes), NMT can automatically replicate the changes implemented by developers during pull requests in up to 36% of the cases.
no code implementations • 27 Dec 2018 • Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, Denys Poshyvanyk
Starting from code fixed by developers in the context of a bug-fix, our empirical evaluation showed that our models are able to predict mutants that resemble original fixed bugs in between 9% and 45% of the cases (depending on the model).
Software Engineering
2 code implementations • 24 Dec 2018 • Zimin Chen, Steve Kommrusch, Michele Tufano, Louis-Noël Pouchet, Denys Poshyvanyk, Martin Monperrus
This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning.
no code implementations • 7 Feb 2018 • Kevin Moran, Carlos Bernal-Cárdenas, Michael Curcio, Richard Bonett, Denys Poshyvanyk
It is common practice for developers of user-facing software to transform a mock-up of a graphical user interface (GUI) into code.
1 code implementation • 15 Jul 2017 • Martin White, Michele Tufano, Matias Martinez, Martin Monperrus, Denys Poshyvanyk
We aim to reason about the repair ingredients by using code similarities to prioritize and transform statements in a codebase for patch generation.
Software Engineering