Learning syntactic program transformations from examples

R Rolim, G Soares, L D'Antoni… - 2017 IEEE/ACM 39th …, 2017 - ieeexplore.ieee.org
Automatic program transformation tools can be valuable for programmers to help them with
refactoring tasks, and for Computer Science students in the form of tutoring systems that …

On multi-modal learning of editing source code

S Chakraborty, B Ray - 2021 36th IEEE/ACM International …, 2021 - ieeexplore.ieee.org
In recent years, Neural Machine Translator (NMT) has shown promise in automatically
editing source code. Typical NMT based code editor only considers the code that needs to …

Codit: Code editing with tree-based neural models

S Chakraborty, Y Ding, M Allamanis… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
The way developers edit day-to-day code tends to be repetitive, often using existing code
elements. Many researchers have tried to automate repetitive code changes by learning …

A graph-based approach to API usage adaptation

HA Nguyen, TT Nguyen, G Wilson Jr, AT Nguyen… - ACM Sigplan …, 2010 - dl.acm.org
Reusing existing library components is essential for reducing the cost of software
development and maintenance. When library components evolve to accommodate new …

Statistical learning approach for mining API usage mappings for code migration

AT Nguyen, HA Nguyen, TT Nguyen… - Proceedings of the 29th …, 2014 - dl.acm.org
The same software product nowadays could appear in multiple platforms and devices. To
address business needs, software companies develop a software product in a programming …

Divide-and-conquer approach for multi-phase statistical migration for source code (t)

AT Nguyen, TT Nguyen… - 2015 30th IEEE/ACM …, 2015 - ieeexplore.ieee.org
Prior research shows that directly applying phrase-based SMT on lexical tokens to migrate
Java to C# produces much semantically incorrect code. A key limitation is the use of …

Grace: Language models meet code edits

P Gupta, A Khare, Y Bajpai, S Chakraborty… - Proceedings of the 31st …, 2023 - dl.acm.org
Developers spend a significant amount of time in editing code for a variety of reasons such
as bug fixing or adding new features. Designing effective methods to predict code edits has …

Multilingual Program Code Classification Using -Layered Bi-LSTM Model With Optimized Hyperparameters

MM Rahman, Y Watanobe - IEEE Transactions on Emerging …, 2023 - ieeexplore.ieee.org
Programmers are allowed to solve problems using multiple programming languages,
resulting in the accumulation of a huge number of multilingual solution codes …

Refactoring references for library migration

P Kapur, B Cossette, RJ Walker - … of the ACM international conference on …, 2010 - dl.acm.org
Automated refactoring is a key feature of modern IDEs. Existing refactorings rely on the
transformation of source code declarations, in which references may also be transformed as …

Migrating gradual types

JP Campora, S Chen, M Erwig… - Proceedings of the ACM …, 2017 - dl.acm.org
Gradual typing allows programs to enjoy the benefits of both static typing and dynamic
typing. While it is often desirable to migrate a program from more dynamically-typed to more …