@inproceedings{diera-etal-2023-gencodesearchnet,
title = "{G}en{C}ode{S}earch{N}et: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding",
author = "Diera, Andor and
Dahou, Abdelhalim and
Galke, Lukas and
Karl, Fabian and
Sihler, Florian and
Scherp, Ansgar",
editor = "Hupkes, Dieuwke and
Dankers, Verna and
Batsuren, Khuyagbaatar and
Sinha, Koustuv and
Kazemnejad, Amirhossein and
Christodoulopoulos, Christos and
Cotterell, Ryan and
Bruni, Elia",
booktitle = "Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.genbench-1.2",
doi = "10.18653/v1/2023.genbench-1.2",
pages = "12--24",
abstract = "Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries. These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP generalization taxonomy proposed by Hupkes et.,al., we propose a new benchmark dataset called GenCodeSearchNet (GeCS) which builds upon existing natural language code search datasets to systemically evaluate the programming language understanding generalization capabilities of language models. As part of the full dataset, we introduce a new, manually curated subset StatCodeSearch that focuses on R, a popular but so far underrepresented programming language that is often used by researchers outside the field of computer science. For evaluation and comparison, we collect several baseline results using fine-tuned BERT-style models and GPT-style large language models in a zero-shot setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diera-etal-2023-gencodesearchnet">
<titleInfo>
<title>GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andor</namePart>
<namePart type="family">Diera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelhalim</namePart>
<namePart type="family">Dahou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="family">Galke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Karl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Sihler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ansgar</namePart>
<namePart type="family">Scherp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verna</namePart>
<namePart type="family">Dankers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khuyagbaatar</namePart>
<namePart type="family">Batsuren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustuv</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Kazemnejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries. These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP generalization taxonomy proposed by Hupkes et.,al., we propose a new benchmark dataset called GenCodeSearchNet (GeCS) which builds upon existing natural language code search datasets to systemically evaluate the programming language understanding generalization capabilities of language models. As part of the full dataset, we introduce a new, manually curated subset StatCodeSearch that focuses on R, a popular but so far underrepresented programming language that is often used by researchers outside the field of computer science. For evaluation and comparison, we collect several baseline results using fine-tuned BERT-style models and GPT-style large language models in a zero-shot setting.</abstract>
<identifier type="citekey">diera-etal-2023-gencodesearchnet</identifier>
<identifier type="doi">10.18653/v1/2023.genbench-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.genbench-1.2</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
%A Diera, Andor
%A Dahou, Abdelhalim
%A Galke, Lukas
%A Karl, Fabian
%A Sihler, Florian
%A Scherp, Ansgar
%Y Hupkes, Dieuwke
%Y Dankers, Verna
%Y Batsuren, Khuyagbaatar
%Y Sinha, Koustuv
%Y Kazemnejad, Amirhossein
%Y Christodoulopoulos, Christos
%Y Cotterell, Ryan
%Y Bruni, Elia
%S Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F diera-etal-2023-gencodesearchnet
%X Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries. These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP generalization taxonomy proposed by Hupkes et.,al., we propose a new benchmark dataset called GenCodeSearchNet (GeCS) which builds upon existing natural language code search datasets to systemically evaluate the programming language understanding generalization capabilities of language models. As part of the full dataset, we introduce a new, manually curated subset StatCodeSearch that focuses on R, a popular but so far underrepresented programming language that is often used by researchers outside the field of computer science. For evaluation and comparison, we collect several baseline results using fine-tuned BERT-style models and GPT-style large language models in a zero-shot setting.
%R 10.18653/v1/2023.genbench-1.2
%U https://aclanthology.org/2023.genbench-1.2
%U https://doi.org/10.18653/v1/2023.genbench-1.2
%P 12-24
Markdown (Informal)
[GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding](https://aclanthology.org/2023.genbench-1.2) (Diera et al., GenBench-WS 2023)
ACL