@inproceedings{reymond-steinert-threlkeld-2023-mscan,
title = "m{SCAN}: A Dataset for Multilingual Compositional Generalisation Evaluation",
author = "Reymond, Am{\'e}lie and
Steinert-Threlkeld, Shane",
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-1.11/",
doi = "10.18653/v1/2023.genbench-1.11",
pages = "143--151",
abstract = "Language models achieve remarkable results on a variety of tasks, yet still struggle on compositional generalisation benchmarks. The majority of these benchmarks evaluate performance in English only, leaving us with the question of whether these results generalise to other languages. As an initial step to answering this question, we introduce mSCAN, a multilingual adaptation of the SCAN dataset. It was produced by a rule-based translation, developed in cooperation with native speakers. We then showcase this novel dataset on some in-context learning experiments, and GPT3.5 and the multilingual large language model BLOOM as well as gpt3.5-turbo."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reymond-steinert-threlkeld-2023-mscan">
<titleInfo>
<title>mSCAN: A Dataset for Multilingual Compositional Generalisation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amélie</namePart>
<namePart type="family">Reymond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shane</namePart>
<namePart type="family">Steinert-Threlkeld</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 achieve remarkable results on a variety of tasks, yet still struggle on compositional generalisation benchmarks. The majority of these benchmarks evaluate performance in English only, leaving us with the question of whether these results generalise to other languages. As an initial step to answering this question, we introduce mSCAN, a multilingual adaptation of the SCAN dataset. It was produced by a rule-based translation, developed in cooperation with native speakers. We then showcase this novel dataset on some in-context learning experiments, and GPT3.5 and the multilingual large language model BLOOM as well as gpt3.5-turbo.</abstract>
<identifier type="citekey">reymond-steinert-threlkeld-2023-mscan</identifier>
<identifier type="doi">10.18653/v1/2023.genbench-1.11</identifier>
<location>
<url>https://aclanthology.org/2023.genbench-1.11/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>143</start>
<end>151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mSCAN: A Dataset for Multilingual Compositional Generalisation Evaluation
%A Reymond, Amélie
%A Steinert-Threlkeld, Shane
%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 reymond-steinert-threlkeld-2023-mscan
%X Language models achieve remarkable results on a variety of tasks, yet still struggle on compositional generalisation benchmarks. The majority of these benchmarks evaluate performance in English only, leaving us with the question of whether these results generalise to other languages. As an initial step to answering this question, we introduce mSCAN, a multilingual adaptation of the SCAN dataset. It was produced by a rule-based translation, developed in cooperation with native speakers. We then showcase this novel dataset on some in-context learning experiments, and GPT3.5 and the multilingual large language model BLOOM as well as gpt3.5-turbo.
%R 10.18653/v1/2023.genbench-1.11
%U https://aclanthology.org/2023.genbench-1.11/
%U https://doi.org/10.18653/v1/2023.genbench-1.11
%P 143-151
Markdown (Informal)
[mSCAN: A Dataset for Multilingual Compositional Generalisation Evaluation](https://aclanthology.org/2023.genbench-1.11/) (Reymond & Steinert-Threlkeld, GenBench 2023)
ACL