@inproceedings{zyrianova-kalpakchi-2023-qua,
title = "{QUA}-{RC}: the semi-synthetic dataset of multiple choice questions for assessing reading comprehension in {U}krainian",
author = "Zyrianova, Mariia and
Kalpakchi, Dmytro",
editor = "Derczynski, Leon",
booktitle = "Northern European Journal of Language Technology, Volume 9",
year = "2023",
address = {Link{\"o}ping, Sweden},
publisher = {Link{\"o}ping University Electronic Press},
url = "https://aclanthology.org/2023.nejlt-1.10",
doi = "https://doi.org/10.3384/nejlt.2000-1533.2023.4939",
abstract = "In this article we present the first dataset of multiple choice questions for assessing reading comprehension in Ukrainian. The dataset is based on the texts from the Ukrainian national tests for reading comprehension, and the MCQs themselves are created semi-automatically in three stages. The first stage was to use GPT-3 to generate the MCQs zero-shot, the second stage was to select MCQs of sufficient quality and revise the ones with minor errors, whereas the final stage was to expand the dataset with the MCQs written manually. The dataset is created by the Ukrainian language native speakers, one of whom is also a language teacher. The resulting corpus has slightly more than 900 MCQs, of which only 43 MCQs could be kept as they were generated by GPT-3.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zyrianova-kalpakchi-2023-qua">
<titleInfo>
<title>QUA-RC: the semi-synthetic dataset of multiple choice questions for assessing reading comprehension in Ukrainian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariia</namePart>
<namePart type="family">Zyrianova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmytro</namePart>
<namePart type="family">Kalpakchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Northern European Journal of Language Technology, Volume 9</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press</publisher>
<place>
<placeTerm type="text">Linköping, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this article we present the first dataset of multiple choice questions for assessing reading comprehension in Ukrainian. The dataset is based on the texts from the Ukrainian national tests for reading comprehension, and the MCQs themselves are created semi-automatically in three stages. The first stage was to use GPT-3 to generate the MCQs zero-shot, the second stage was to select MCQs of sufficient quality and revise the ones with minor errors, whereas the final stage was to expand the dataset with the MCQs written manually. The dataset is created by the Ukrainian language native speakers, one of whom is also a language teacher. The resulting corpus has slightly more than 900 MCQs, of which only 43 MCQs could be kept as they were generated by GPT-3.</abstract>
<identifier type="citekey">zyrianova-kalpakchi-2023-qua</identifier>
<identifier type="doi">https://doi.org/10.3384/nejlt.2000-1533.2023.4939</identifier>
<location>
<url>https://aclanthology.org/2023.nejlt-1.10</url>
</location>
<part>
<date>2023</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUA-RC: the semi-synthetic dataset of multiple choice questions for assessing reading comprehension in Ukrainian
%A Zyrianova, Mariia
%A Kalpakchi, Dmytro
%Y Derczynski, Leon
%S Northern European Journal of Language Technology, Volume 9
%D 2023
%I Linköping University Electronic Press
%C Linköping, Sweden
%F zyrianova-kalpakchi-2023-qua
%X In this article we present the first dataset of multiple choice questions for assessing reading comprehension in Ukrainian. The dataset is based on the texts from the Ukrainian national tests for reading comprehension, and the MCQs themselves are created semi-automatically in three stages. The first stage was to use GPT-3 to generate the MCQs zero-shot, the second stage was to select MCQs of sufficient quality and revise the ones with minor errors, whereas the final stage was to expand the dataset with the MCQs written manually. The dataset is created by the Ukrainian language native speakers, one of whom is also a language teacher. The resulting corpus has slightly more than 900 MCQs, of which only 43 MCQs could be kept as they were generated by GPT-3.
%R https://doi.org/10.3384/nejlt.2000-1533.2023.4939
%U https://aclanthology.org/2023.nejlt-1.10
%U https://doi.org/https://doi.org/10.3384/nejlt.2000-1533.2023.4939
Markdown (Informal)
[QUA-RC: the semi-synthetic dataset of multiple choice questions for assessing reading comprehension in Ukrainian](https://aclanthology.org/2023.nejlt-1.10) (Zyrianova & Kalpakchi, NEJLT 2023)
ACL