@inproceedings{kondo-etal-2024-improving,
title = "Improving Repository-level Code Search with Text Conversion",
author = "Kondo, Mizuki and
Kawahara, Daisuke and
Kurabayashi, Toshiyuki",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia and
Zampieri, Marcos and
Ferraro, Francis and
Swayamdipta, Swabha",
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.15",
doi = "10.18653/v1/2024.naacl-srw.15",
pages = "130--137",
abstract = "The ability to generate code using large language models (LLMs) has been increasing year by year. However, studies on code generation at the repository level are not very active. In repository-level code generation, it is necessary to refer to related code snippets among multiple files. By taking the similarity between code snippets, related files are searched and input into an LLM, and generation is performed. This paper proposes a method to search for related files (code search) by taking similarities not between code snippets but between the texts converted from the code snippets by the LLM. We confirmed that converting to text improves the accuracy of code search.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kondo-etal-2024-improving">
<titleInfo>
<title>Improving Repository-level Code Search with Text Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mizuki</namePart>
<namePart type="family">Kondo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiyuki</namePart>
<namePart type="family">Kurabayashi</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>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Ferraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</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>The ability to generate code using large language models (LLMs) has been increasing year by year. However, studies on code generation at the repository level are not very active. In repository-level code generation, it is necessary to refer to related code snippets among multiple files. By taking the similarity between code snippets, related files are searched and input into an LLM, and generation is performed. This paper proposes a method to search for related files (code search) by taking similarities not between code snippets but between the texts converted from the code snippets by the LLM. We confirmed that converting to text improves the accuracy of code search.</abstract>
<identifier type="citekey">kondo-etal-2024-improving</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-srw.15</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.15</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>130</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Repository-level Code Search with Text Conversion
%A Kondo, Mizuki
%A Kawahara, Daisuke
%A Kurabayashi, Toshiyuki
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%Y Zampieri, Marcos
%Y Ferraro, Francis
%Y Swayamdipta, Swabha
%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 kondo-etal-2024-improving
%X The ability to generate code using large language models (LLMs) has been increasing year by year. However, studies on code generation at the repository level are not very active. In repository-level code generation, it is necessary to refer to related code snippets among multiple files. By taking the similarity between code snippets, related files are searched and input into an LLM, and generation is performed. This paper proposes a method to search for related files (code search) by taking similarities not between code snippets but between the texts converted from the code snippets by the LLM. We confirmed that converting to text improves the accuracy of code search.
%R 10.18653/v1/2024.naacl-srw.15
%U https://aclanthology.org/2024.naacl-srw.15
%U https://doi.org/10.18653/v1/2024.naacl-srw.15
%P 130-137
Markdown (Informal)
[Improving Repository-level Code Search with Text Conversion](https://aclanthology.org/2024.naacl-srw.15) (Kondo et al., NAACL 2024)
ACL
- Mizuki Kondo, Daisuke Kawahara, and Toshiyuki Kurabayashi. 2024. Improving Repository-level Code Search with Text Conversion. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 130–137, Mexico City, Mexico. Association for Computational Linguistics.