<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="villmow-etal-2022-addressing">
    <titleInfo>
        <title>Addressing Leakage in Self-Supervised Contextualized Code Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Johannes</namePart>
        <namePart type="family">Villmow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Viola</namePart>
        <namePart type="family">Campos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adrian</namePart>
        <namePart type="family">Ulges</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ulrich</namePart>
        <namePart type="family">Schwanecke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 29th International Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into contexts and targets. To combat leakage between the two, we suggest a novel approach based on mutual identifier masking, dedentation, and the selection of syntax-aligned targets. Our second contribution is a new dataset for direct evaluation of contextualized code retrieval, based on a dataset of manually aligned subpassages of code clones. Our experiments demonstrate that the proposed approach improves retrieval substantially, and yields new state-of-the-art results for code clone and defect detection.</abstract>
    <identifier type="citekey">villmow-etal-2022-addressing</identifier>
    <location>
        <url>https://aclanthology.org/2022.coling-1.84</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>1006</start>
            <end>1013</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Addressing Leakage in Self-Supervised Contextualized Code Retrieval
%A Villmow, Johannes
%A Campos, Viola
%A Ulges, Adrian
%A Schwanecke, Ulrich
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F villmow-etal-2022-addressing
%X We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into contexts and targets. To combat leakage between the two, we suggest a novel approach based on mutual identifier masking, dedentation, and the selection of syntax-aligned targets. Our second contribution is a new dataset for direct evaluation of contextualized code retrieval, based on a dataset of manually aligned subpassages of code clones. Our experiments demonstrate that the proposed approach improves retrieval substantially, and yields new state-of-the-art results for code clone and defect detection.
%U https://aclanthology.org/2022.coling-1.84
%P 1006-1013

Markdown (Informal)

[Addressing Leakage in Self-Supervised Contextualized Code Retrieval](https://aclanthology.org/2022.coling-1.84) (Villmow et al., COLING 2022)

• Addressing Leakage in Self-Supervised Contextualized Code Retrieval (Villmow et al., COLING 2022)

ACL

• Johannes Villmow, Viola Campos, Adrian Ulges, and Ulrich Schwanecke. 2022. Addressing Leakage in Self-Supervised Contextualized Code Retrieval. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1006–1013, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.