Results 11 to 20 of about 12,796,570 (330)
NatGen: generative pre-training by “naturalizing” source code [PDF]
ESEC/SIGSOFT FSE, 2022 Pre-trained Generative Language models (e.g., PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and translation. These models have adopted varying pre-training objectives to
Saikat Chakraborty +4 more
semanticscholar +1 more source
CoditT5: Pretraining for Source Code and Natural Language Editing [PDF]
International Conference on Automated Software Engineering, 2022 Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits.
Jiyang Zhang +4 more
semanticscholar +1 more source
Applied Sciences, 2023 As artificial intelligence advances, source code completion assistants are becoming more advanced and powerful. Existing traditional assistants are no longer up to all the developers’ challenges.
Tilen Hliš +3 more
doaj +1 more source
A Transformer-based Approach for Source Code Summarization [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Generating a readable summary that describes the functionality of a program is known as source code summarization. In this task, learning code representation by modeling the pairwise relationship between code tokens to capture their long-range ...
Wasi Uddin Ahmad +3 more
semanticscholar +1 more source
Semantic similarity metrics for evaluating source code summarization [PDF]
IEEE International Conference on Program Comprehension, 2022 Source code summarization involves creating brief descriptions of source code in natural language. These descriptions are a key component of software documentation such as JavaDocs.
S. Haque +3 more
semanticscholar +1 more source
EditSum: A Retrieve-and-Edit Framework for Source Code Summarization [PDF]
International Conference on Automated Software Engineering, 2021 Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects.
Jia Li +5 more
semanticscholar +1 more source
BIOPLAG: An Approach to Detect Programming Plagiarism
Anais da Academia Brasileira de Ciências, 2023 This paper creates an approach to the automatic detection of plagiarism in programming by combining the interdisciplinary knowledge from bioinformatics with techniques such as: tokens of programming language elements, tokens mapping in synthetic ...
KAIO P. GOMES +2 more
doaj +1 more source
PAC Codes for Source and Joint Source-Channel Coding
2023 IEEE Globecom Workshops (GC Wkshps), 2023 Polarization-adjusted convolutional (PAC) codes, as a concatenated coding scheme based on polar codes, is able to approach the finite-length bound of binary-input AWGN channel at short blocklengths. In this paper, we extend PAC codes to the fields of source coding and joint source-channel coding and show that they can also approach the corresponding ...
Mengfan Zheng, Cong Ling 0001
openaire +2 more sources
Authorship Identification of Binary and Disassembled Codes Using NLP Methods
Information, 2023 This article is part of a series aimed at determining the authorship of source codes. Analyzing binary code is a crucial aspect of cybersecurity, software development, and computer forensics, particularly in identifying malware authors.
Aleksandr Romanov +3 more
doaj +1 more source
On Multi-Modal Learning of Editing Source Code [PDF]
International Conference on Automated Software Engineering, 2021 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 be changed as input and suggests developers with a ranked list of patched code to
Saikat Chakraborty, Baishakhi Ray
semanticscholar +1 more source