@inproceedings{gong-etal-2022-khanq,
title = "{KHANQ}: A Dataset for Generating Deep Questions in Education",
author = "Gong, Huanli and
Pan, Liangming and
Hu, Hengchang",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.518",
pages = "5925--5938",
abstract = "Designing in-depth educational questions is a time-consuming and cognitively demanding task. Therefore, it is intriguing to study how to build Question Generation (QG) models to automate the question creation process. However, existing QG datasets are not suitable for educational question generation because the questions are not real questions asked by humans during learning and can be solved by simply searching for information. To bridge this gap, we present KHANQ, a challenging dataset for educational question generation, containing 1,034 high-quality learner-generated questions seeking an in-depth understanding of the taught online courses in Khan Academy. Each data sample is carefully paraphrased and annotated as a triple of 1) Context: an independent paragraph on which the question is based; 2) Prompt: a text prompt for the question (e.g., the learner{'}s background knowledge); 3) Question: a deep question based on Context and coherent with Prompt. By conducting a human evaluation on the aspects of appropriateness, coverage, coherence, and complexity, we show that state-of-the-art QG models which perform well on shallow question generation datasets have difficulty in generating useful educational questions. This makes KHANQ a challenging testbed for educational question generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2022-khanq">
<titleInfo>
<title>KHANQ: A Dataset for Generating Deep Questions in Education</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huanli</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangming</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchang</namePart>
<namePart type="family">Hu</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>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Designing in-depth educational questions is a time-consuming and cognitively demanding task. Therefore, it is intriguing to study how to build Question Generation (QG) models to automate the question creation process. However, existing QG datasets are not suitable for educational question generation because the questions are not real questions asked by humans during learning and can be solved by simply searching for information. To bridge this gap, we present KHANQ, a challenging dataset for educational question generation, containing 1,034 high-quality learner-generated questions seeking an in-depth understanding of the taught online courses in Khan Academy. Each data sample is carefully paraphrased and annotated as a triple of 1) Context: an independent paragraph on which the question is based; 2) Prompt: a text prompt for the question (e.g., the learner’s background knowledge); 3) Question: a deep question based on Context and coherent with Prompt. By conducting a human evaluation on the aspects of appropriateness, coverage, coherence, and complexity, we show that state-of-the-art QG models which perform well on shallow question generation datasets have difficulty in generating useful educational questions. This makes KHANQ a challenging testbed for educational question generation.</abstract>
<identifier type="citekey">gong-etal-2022-khanq</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.518</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5925</start>
<end>5938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KHANQ: A Dataset for Generating Deep Questions in Education
%A Gong, Huanli
%A Pan, Liangming
%A Hu, Hengchang
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%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 gong-etal-2022-khanq
%X Designing in-depth educational questions is a time-consuming and cognitively demanding task. Therefore, it is intriguing to study how to build Question Generation (QG) models to automate the question creation process. However, existing QG datasets are not suitable for educational question generation because the questions are not real questions asked by humans during learning and can be solved by simply searching for information. To bridge this gap, we present KHANQ, a challenging dataset for educational question generation, containing 1,034 high-quality learner-generated questions seeking an in-depth understanding of the taught online courses in Khan Academy. Each data sample is carefully paraphrased and annotated as a triple of 1) Context: an independent paragraph on which the question is based; 2) Prompt: a text prompt for the question (e.g., the learner’s background knowledge); 3) Question: a deep question based on Context and coherent with Prompt. By conducting a human evaluation on the aspects of appropriateness, coverage, coherence, and complexity, we show that state-of-the-art QG models which perform well on shallow question generation datasets have difficulty in generating useful educational questions. This makes KHANQ a challenging testbed for educational question generation.
%U https://aclanthology.org/2022.coling-1.518
%P 5925-5938
Markdown (Informal)
[KHANQ: A Dataset for Generating Deep Questions in Education](https://aclanthology.org/2022.coling-1.518) (Gong et al., COLING 2022)
ACL