@inproceedings{rahaman-ive-2024-source,
title = "Source Code is a Graph, Not a Sequence: A Cross-Lingual Perspective on Code Clone Detection",
author = "Rahaman, Mohammed and
Ive, Julia",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.20",
pages = "168--199",
abstract = "Code clone detection is challenging, as sourcecode can be written in different languages, do-mains, and styles. In this paper, we arguethat source code is inherently a graph, not asequence, and that graph-based methods aremore suitable for code clone detection thansequence-based methods. We compare the per-formance of two state-of-the-art models: Code-BERT (Feng et al., 2020), a sequence-basedmodel, and CodeGraph (Yu et al., 2023), agraph-based model, on two benchmark data-sets: BCB (Svajlenko et al., 2014) and PoolC(PoolC, no date). We show that CodeGraphoutperforms CodeBERT on both data-sets, es-pecially on cross-lingual code clones. To thebest of our knowledge, this is the first work todemonstrate the cross-lingual code clone detec-tion showing superiority on graph-based meth-ods over sequence-based methods",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahaman-ive-2024-source">
<titleInfo>
<title>Source Code is a Graph, Not a Sequence: A Cross-Lingual Perspective on Code Clone Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Rahaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Ive</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code clone detection is challenging, as sourcecode can be written in different languages, do-mains, and styles. In this paper, we arguethat source code is inherently a graph, not asequence, and that graph-based methods aremore suitable for code clone detection thansequence-based methods. We compare the per-formance of two state-of-the-art models: Code-BERT (Feng et al., 2020), a sequence-basedmodel, and CodeGraph (Yu et al., 2023), agraph-based model, on two benchmark data-sets: BCB (Svajlenko et al., 2014) and PoolC(PoolC, no date). We show that CodeGraphoutperforms CodeBERT on both data-sets, es-pecially on cross-lingual code clones. To thebest of our knowledge, this is the first work todemonstrate the cross-lingual code clone detec-tion showing superiority on graph-based meth-ods over sequence-based methods</abstract>
<identifier type="citekey">rahaman-ive-2024-source</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.20</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>168</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Source Code is a Graph, Not a Sequence: A Cross-Lingual Perspective on Code Clone Detection
%A Rahaman, Mohammed
%A Ive, Julia
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rahaman-ive-2024-source
%X Code clone detection is challenging, as sourcecode can be written in different languages, do-mains, and styles. In this paper, we arguethat source code is inherently a graph, not asequence, and that graph-based methods aremore suitable for code clone detection thansequence-based methods. We compare the per-formance of two state-of-the-art models: Code-BERT (Feng et al., 2020), a sequence-basedmodel, and CodeGraph (Yu et al., 2023), agraph-based model, on two benchmark data-sets: BCB (Svajlenko et al., 2014) and PoolC(PoolC, no date). We show that CodeGraphoutperforms CodeBERT on both data-sets, es-pecially on cross-lingual code clones. To thebest of our knowledge, this is the first work todemonstrate the cross-lingual code clone detec-tion showing superiority on graph-based meth-ods over sequence-based methods
%U https://aclanthology.org/2024.naacl-srw.20
%P 168-199
Markdown (Informal)
[Source Code is a Graph, Not a Sequence: A Cross-Lingual Perspective on Code Clone Detection](https://aclanthology.org/2024.naacl-srw.20) (Rahaman & Ive, NAACL 2024)
ACL