A survey of machine learning for big code and naturalness
Research at the intersection of machine learning, programming languages, and software
engineering has recently taken important steps in proposing learnable probabilistic models …
engineering has recently taken important steps in proposing learnable probabilistic models …
Deep learning for source code modeling and generation: Models, applications, and challenges
Deep Learning (DL) techniques for Natural Language Processing have been evolving
remarkably fast. Recently, the DL advances in language modeling, machine translation, and …
remarkably fast. Recently, the DL advances in language modeling, machine translation, and …
Unsupervised translation of programming languages
B Roziere, MA Lachaux… - Advances in neural …, 2020 - proceedings.neurips.cc
A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …
code from a high-level programming language (such as C++ or Python) to another …
Unsupervised translation of programming languages
A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …
code from a high-level programming language (such as C++ or Python) to another …
Multi-lingual evaluation of code generation models
We present new benchmarks on evaluation code generation models: MBXP and Multilingual
HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are …
HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are …
Leveraging automated unit tests for unsupervised code translation
With little to no parallel data available for programming languages, unsupervised methods
are well-suited to source code translation. However, the majority of unsupervised machine …
are well-suited to source code translation. However, the majority of unsupervised machine …
Code translation with compiler representations
In this paper, we leverage low-level compiler intermediate representations (IR) to improve
code translation. Traditional transpilers rely on syntactic information and handcrafted rules …
code translation. Traditional transpilers rely on syntactic information and handcrafted rules …
Avatar: A parallel corpus for java-python program translation
WU Ahmad, MGR Tushar, S Chakraborty… - arXiv preprint arXiv …, 2021 - arxiv.org
Program translation refers to migrating source code from one programming language to
another. It has tremendous practical value in software development, as porting software …
another. It has tremendous practical value in software development, as porting software …
Automated transpilation of imperative to functional code using neural-guided program synthesis
While many mainstream languages such as Java, Python, and C# increasingly incorporate
functional APIs to simplify programming and improve parallelization/performance, there are …
functional APIs to simplify programming and improve parallelization/performance, there are …
Summarize and generate to back-translate: Unsupervised translation of programming languages
Back-translation is widely known for its effectiveness in neural machine translation when
there is little to no parallel data. In this approach, a source-to-target model is coupled with a …
there is little to no parallel data. In this approach, a source-to-target model is coupled with a …