@inproceedings{wang-etal-2023-mconala,
title = "{MC}o{N}a{L}a: A Benchmark for Code Generation from Multiple Natural Languages",
author = "Wang, Zhiruo and
Cuenca, Grace and
Zhou, Shuyan and
Xu, Frank F. and
Neubig, Graham",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.20/",
doi = "10.18653/v1/2023.findings-eacl.20",
pages = "265--273",
abstract = "While there has been a recent burgeoning of applications at the intersection of natural and programming languages, such as code generation and code summarization, these applications are usually English-centric. This creates a barrier for program developers who are not proficient in English. To mitigate this gap in technology development across languages, we propose a multilingual dataset, MCoNaLa, to benchmark code generation from natural language commands extending beyond English. Modeled off of the methodology from the English Code/Natural Language Challenge (CoNaLa) dataset, we annotated a total of 896 NL-Code pairs in three languages: Spanish, Japanese, and Russian. We present a systematic evaluation on MCoNaLa by testing state-of-the-art code generation systems. Although the difficulties vary across three languages, all systems lag significantly behind their English counterparts, revealing the challenges in adapting code generation to new languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-mconala">
<titleInfo>
<title>MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiruo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="family">Cuenca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While there has been a recent burgeoning of applications at the intersection of natural and programming languages, such as code generation and code summarization, these applications are usually English-centric. This creates a barrier for program developers who are not proficient in English. To mitigate this gap in technology development across languages, we propose a multilingual dataset, MCoNaLa, to benchmark code generation from natural language commands extending beyond English. Modeled off of the methodology from the English Code/Natural Language Challenge (CoNaLa) dataset, we annotated a total of 896 NL-Code pairs in three languages: Spanish, Japanese, and Russian. We present a systematic evaluation on MCoNaLa by testing state-of-the-art code generation systems. Although the difficulties vary across three languages, all systems lag significantly behind their English counterparts, revealing the challenges in adapting code generation to new languages.</abstract>
<identifier type="citekey">wang-etal-2023-mconala</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.20</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.20/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>265</start>
<end>273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages
%A Wang, Zhiruo
%A Cuenca, Grace
%A Zhou, Shuyan
%A Xu, Frank F.
%A Neubig, Graham
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F wang-etal-2023-mconala
%X While there has been a recent burgeoning of applications at the intersection of natural and programming languages, such as code generation and code summarization, these applications are usually English-centric. This creates a barrier for program developers who are not proficient in English. To mitigate this gap in technology development across languages, we propose a multilingual dataset, MCoNaLa, to benchmark code generation from natural language commands extending beyond English. Modeled off of the methodology from the English Code/Natural Language Challenge (CoNaLa) dataset, we annotated a total of 896 NL-Code pairs in three languages: Spanish, Japanese, and Russian. We present a systematic evaluation on MCoNaLa by testing state-of-the-art code generation systems. Although the difficulties vary across three languages, all systems lag significantly behind their English counterparts, revealing the challenges in adapting code generation to new languages.
%R 10.18653/v1/2023.findings-eacl.20
%U https://aclanthology.org/2023.findings-eacl.20/
%U https://doi.org/10.18653/v1/2023.findings-eacl.20
%P 265-273
Markdown (Informal)
[MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages](https://aclanthology.org/2023.findings-eacl.20/) (Wang et al., Findings 2023)
ACL