DeepClone: Modeling Clones to Generate Code Predictions

Hammad, Muhammad; Babur, Önder; Basit, Hamid Abdul; Brand, Mark van den

doi:10.1007/978-3-030-64694-3_9

Cited by 8 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we describe how we perform language modeling and how we construct the DeepClone model ( Hammad et al, 2020a ) by conducting a detailed empirical evaluation on the model quality and accuracy for the token prediction task.…”

Section: Methodsmentioning

confidence: 99%

“…It contains validated clone methods belonging to 43 different functionalities, for instance, “copy file” functionality contains 3,055 different implementations. Further details can be found from our previous paper ( Hammad et al, 2020a ), and BigCloneBench dataset. Hence, it is possible to have Clone-Advisor recommendations that do not exactly match the ground truth but match its functionality.…”

Section: Empirical Evaluationmentioning

confidence: 99%

“…In previous work, we introduced DeepClone ( Hammad et al, 2020a ), a DNN model trained by fine-tuning GPT-2 over the BigCloneBench code clone dataset, for predicting code tokens and clone methods. The proposed approach has already led to promising results.…”

Section: Introductionmentioning

confidence: 99%

“…We believe that our approach can help in improving the quality of code prediction based on user input. In this work, we have made the following contributions: We elaborate our previous work on DeepClone ( Hammad et al, 2020a ) model with more related work and details, and provide an evaluation of DeepClone output in terms of perplexity scores. We refine the raw output of DeepClone model with a novel approach called Clone-Advisor, for recommending real clone methods, using an IR technique (TF-IDF) for retrieving the most relevant clone methods from a search corpus.…”

Section: Introductionmentioning

confidence: 99%

“…We elaborate our previous work on DeepClone ( Hammad et al, 2020a ) model with more related work and details, and provide an evaluation of DeepClone output in terms of perplexity scores.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Hammad

Babur

Basit

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Empirical Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…We elaborate our previous work on DeepClone ( Hammad et al, 2020a ) model with more related work and details, and provide an evaluation of DeepClone output in terms of perplexity scores.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Hammad

Babur

Basit

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

BigCloneBench

Svajlenko

Roy

2021

Code Clone Analysis

View full text Add to dashboard Cite

Source code auto-completion using various deep learning models under limited computing resources

Sharma

Mishra

Kumar

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Deep learning models have become state of the art in many language modelling tasks. Among such tasks, source code auto-completion is one of the important areas of research. This paper presents various methodologies for source code auto-completion using different Deep Learning models for Python and CSharp Programming Languages. In a resource-limited environment, it is paramount to reduce various overheads: one way of achieving that is to use the code sequences to train and evaluate rather than using other code structures such as semantics. This paper compares various deep learning architectures like CodeGPT [1] from Microsoft, Roberta [2] from huggingface [3] and GPT2 [4] for source code auto-completion. Different dataset strategies are employed for comparison, such as (1) treating the whole code file as a single line, (2) using each line as single individual inputs, and (3) tokenizing the codes snippets before feeding them into the models. We consider the task of autocompletion on two different datasets: (1) Python dataset; (2) CSharp dataset. The Python dataset is processed by a fine-tuned CodeGPT with an overall accuracy of 71%. For the CSharp dataset with the GPT2 model, a PPL of 2.14 and 4.082 on the training and evaluation dataset is observed. Considering the results, we discuss the strength and weaknesses of different approaches in their application in the real world programming context.

show abstract

DeepClone: Modeling Clones to Generate Code Predictions

Cited by 8 publications

References 20 publications

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

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

BigCloneBench

Source code auto-completion using various deep learning models under limited computing resources

Contact Info

Product

Resources

About