FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226463316> ?p ?o ?g. }

• W4226463316 endingPage "44" @default.
• W4226463316 startingPage "1" @default.
• W4226463316 abstract "Source code representation learning is the basis of applying artificial intelligence to many software engineering tasks such as code clone detection, algorithm classification, and code summarization. Recently, many works have tried to improve the performance of source code representation from various perspectives, e.g., introducing the structural information of programs into latent representation. However, when dealing with rapidly expanded unlabeled cross-language source code datasets from the Internet, there are still two issues. Firstly, deep learning models for many code-specific tasks still suffer from the lack of high-quality labels. Secondly, the structural differences among programming languages make it more difficult to process multiple languages in a single neural architecture. To address these issues, in this article, we propose a novel Cross -language Code representation with a large-scale pre-training ( XCode ) method. Concretely, we propose to use several abstract syntax trees and ELMo-enhanced variational autoencoders to obtain multiple pre-trained source code language models trained on about 1.5 million code snippets. To fully utilize the knowledge across programming languages, we further propose a Shared Encoder-Decoder (SED) architecture which uses the multi-teacher single-student method to transfer knowledge from the aforementioned pre-trained models to the distilled SED. The pre-trained models and SED will cooperate to better represent the source code. For evaluation, we examine our approach on three typical downstream cross-language tasks, i.e., source code translation, code clone detection, and code-to-code search, on a real-world dataset composed of programming exercises with multiple solutions. Experimental results demonstrate the effectiveness of our proposed approach on cross-language code representations. Meanwhile, our approach performs significantly better than several code representation baselines on different downstream tasks in terms of multiple automatic evaluation metrics." @default.
• W4226463316 created "2022-05-05" @default.
• W4226463316 creator A5017227883 @default.
• W4226463316 creator A5022944148 @default.
• W4226463316 creator A5023164791 @default.
• W4226463316 creator A5025876991 @default.
• W4226463316 creator A5037045029 @default.
• W4226463316 creator A5073239318 @default.
• W4226463316 creator A5079229946 @default.
• W4226463316 date "2022-04-09" @default.
• W4226463316 modified "2023-09-26" @default.
• W4226463316 title "<scp>XCode</scp> : Towards Cross-Language Code Representation with Large-Scale Pre-Training" @default.
• W4226463316 cites W1498436455 @default.
• W4226463316 cites W1731081199 @default.
• W4226463316 cites W1832693441 @default.
• W4226463316 cites W1956340063 @default.
• W4226463316 cites W2064675550 @default.
• W4226463316 cites W2079887492 @default.
• W4226463316 cites W2105816471 @default.
• W4226463316 cites W2131774270 @default.
• W4226463316 cites W2146957318 @default.
• W4226463316 cites W2149788502 @default.
• W4226463316 cites W2194775991 @default.
• W4226463316 cites W2282866165 @default.
• W4226463316 cites W2513738415 @default.
• W4226463316 cites W2531207078 @default.
• W4226463316 cites W2583649498 @default.
• W4226463316 cites W2591591831 @default.
• W4226463316 cites W2606722458 @default.
• W4226463316 cites W2772617084 @default.
• W4226463316 cites W2794601162 @default.
• W4226463316 cites W2808279976 @default.
• W4226463316 cites W2884276923 @default.
• W4226463316 cites W2887255581 @default.
• W4226463316 cites W2888557792 @default.
• W4226463316 cites W2888651608 @default.
• W4226463316 cites W2897767292 @default.
• W4226463316 cites W2899171197 @default.
• W4226463316 cites W2931212643 @default.
• W4226463316 cites W2947683321 @default.
• W4226463316 cites W2949266019 @default.
• W4226463316 cites W2956017828 @default.
• W4226463316 cites W2963081964 @default.
• W4226463316 cites W2963247703 @default.
• W4226463316 cites W2963364041 @default.
• W4226463316 cites W2963736842 @default.
• W4226463316 cites W2963767194 @default.
• W4226463316 cites W2963935794 @default.
• W4226463316 cites W2964150020 @default.
• W4226463316 cites W2964350391 @default.
• W4226463316 cites W2964935470 @default.
• W4226463316 cites W2968179027 @default.
• W4226463316 cites W2971261034 @default.
• W4226463316 cites W2972082064 @default.
• W4226463316 cites W2972758308 @default.
• W4226463316 cites W2979271470 @default.
• W4226463316 cites W2993743533 @default.
• W4226463316 cites W2999343753 @default.
• W4226463316 cites W3000135256 @default.
• W4226463316 cites W3005598269 @default.
• W4226463316 cites W3005951744 @default.
• W4226463316 cites W3010181709 @default.
• W4226463316 cites W3018591247 @default.
• W4226463316 cites W3022560936 @default.
• W4226463316 cites W3034172739 @default.
• W4226463316 cites W3041012898 @default.
• W4226463316 cites W3088611441 @default.
• W4226463316 cites W3090867931 @default.
• W4226463316 cites W3091995628 @default.
• W4226463316 cites W3093415205 @default.
• W4226463316 cites W3098121686 @default.
• W4226463316 cites W3098605233 @default.
• W4226463316 cites W3102527112 @default.
• W4226463316 cites W3146720657 @default.
• W4226463316 cites W3162962341 @default.
• W4226463316 cites W3173450168 @default.
• W4226463316 cites W3208790591 @default.
• W4226463316 cites W3212088361 @default.
• W4226463316 cites W4245415816 @default.
• W4226463316 doi "https://doi.org/10.1145/3506696" @default.
• W4226463316 hasPublicationYear "2022" @default.
• W4226463316 type Work @default.
• W4226463316 citedByCount "0" @default.
• W4226463316 crossrefType "journal-article" @default.
• W4226463316 hasAuthorship W4226463316A5017227883 @default.
• W4226463316 hasAuthorship W4226463316A5022944148 @default.
• W4226463316 hasAuthorship W4226463316A5023164791 @default.
• W4226463316 hasAuthorship W4226463316A5025876991 @default.
• W4226463316 hasAuthorship W4226463316A5037045029 @default.
• W4226463316 hasAuthorship W4226463316A5073239318 @default.
• W4226463316 hasAuthorship W4226463316A5079229946 @default.
• W4226463316 hasConcept C117447612 @default.
• W4226463316 hasConcept C121957198 @default.
• W4226463316 hasConcept C133162039 @default.
• W4226463316 hasConcept C154945302 @default.
• W4226463316 hasConcept C170858558 @default.
• W4226463316 hasConcept C177264268 @default.
• W4226463316 hasConcept C199360897 @default.

• next