Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval

Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones (similar code fragments) accumulated in these repositories represent often repeated functionalities and are candidates for reuse in an exploratory or rapid development. To facilita...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Muhammad Hammad, Önder Babur, Hamid Abdul Basit, Mark van den Brand
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	Language modeling Deep learning Code clone Code prediction Information retrieval Code search Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/bd00bf83c7514fdbb2914d05585a0d04
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bd00bf83c7514fdbb2914d05585a0d04
record_format	dspace
spelling	oai:doaj.org-article:bd00bf83c7514fdbb2914d05585a0d042021-11-11T15:05:12ZClone-advisor: recommending code tokens and clone methods with deep learning and information retrieval10.7717/peerj-cs.7372376-5992https://doaj.org/article/bd00bf83c7514fdbb2914d05585a0d042021-11-01T00:00:00Zhttps://peerj.com/articles/cs-737.pdfhttps://peerj.com/articles/cs-737/https://doaj.org/toc/2376-5992Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones (similar code fragments) accumulated in these repositories represent often repeated functionalities and are candidates for reuse in an exploratory or rapid development. To facilitate code clone reuse, we previously presented DeepClone, a novel deep learning approach for modeling code clones along with non-cloned code to predict the next set of tokens (possibly a complete clone method body) based on the code written so far. The probabilistic nature of language modeling, however, can lead to code output with minor syntax or logic errors. To resolve this, we propose a novel approach called Clone-Advisor. We apply an information retrieval technique on top of DeepClone output to recommend real clone methods closely matching the predicted clone method, thus improving the original output by DeepClone. In this paper we have discussed and refined our previous work on DeepClone in much more detail. Moreover, we have quantitatively evaluated the performance and effectiveness of Clone-Advisor in clone method recommendation.Muhammad HammadÖnder BaburHamid Abdul BasitMark van den BrandPeerJ Inc.articleLanguage modelingDeep learningCode cloneCode predictionInformation retrievalCode searchElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e737 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Language modeling Deep learning Code clone Code prediction Information retrieval Code search Electronic computers. Computer science QA75.5-76.95
spellingShingle	Language modeling Deep learning Code clone Code prediction Information retrieval Code search Electronic computers. Computer science QA75.5-76.95 Muhammad Hammad Önder Babur Hamid Abdul Basit Mark van den Brand Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
description	Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones (similar code fragments) accumulated in these repositories represent often repeated functionalities and are candidates for reuse in an exploratory or rapid development. To facilitate code clone reuse, we previously presented DeepClone, a novel deep learning approach for modeling code clones along with non-cloned code to predict the next set of tokens (possibly a complete clone method body) based on the code written so far. The probabilistic nature of language modeling, however, can lead to code output with minor syntax or logic errors. To resolve this, we propose a novel approach called Clone-Advisor. We apply an information retrieval technique on top of DeepClone output to recommend real clone methods closely matching the predicted clone method, thus improving the original output by DeepClone. In this paper we have discussed and refined our previous work on DeepClone in much more detail. Moreover, we have quantitatively evaluated the performance and effectiveness of Clone-Advisor in clone method recommendation.
format	article
author	Muhammad Hammad Önder Babur Hamid Abdul Basit Mark van den Brand
author_facet	Muhammad Hammad Önder Babur Hamid Abdul Basit Mark van den Brand
author_sort	Muhammad Hammad
title	Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
title_short	Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
title_full	Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
title_fullStr	Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
title_full_unstemmed	Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
title_sort	clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/bd00bf83c7514fdbb2914d05585a0d04
work_keys_str_mv	AT muhammadhammad cloneadvisorrecommendingcodetokensandclonemethodswithdeeplearningandinformationretrieval AT onderbabur cloneadvisorrecommendingcodetokensandclonemethodswithdeeplearningandinformationretrieval AT hamidabdulbasit cloneadvisorrecommendingcodetokensandclonemethodswithdeeplearningandinformationretrieval AT markvandenbrand cloneadvisorrecommendingcodetokensandclonemethodswithdeeplearningandinformationretrieval
_version_	1718437170815959040

Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval

Ejemplares similares