@inproceedings{gollapalli-ng-2022-qsts,
title = "{QSTS}: A Question-Sensitive Text Similarity Measure for Question Generation",
author = "Gollapalli, Sujatha Das and
Ng, See-Kiong",
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-1.337",
pages = "3835--3846",
abstract = "While question generation (QG) has received significant focus in conversation modeling and text generation research, the problems of comparing questions and evaluation of QG models have remained inadequately addressed. Indeed, QG models continue to be evaluated using traditional measures such as BLEU, METEOR, and ROUGE scores which were designed for other text generation problems. We propose QSTS, a novel Question-Sensitive Text Similarity measure for comparing two questions by characterizing their target intent based on question class, named-entity, and semantic similarity information from the two questions. We show that QSTS addresses several shortcomings of existing measures that depend on $n$-gram overlap scores and obtains superior results compared to traditional measures on publicly-available QG datasets. We also collect a novel dataset SimQG, for enabling question similarity research in QG contexts. SimQG contains questions generated by state-of-the-art QG models along with human judgements on their relevance with respect to the passage context they were generated for as well as when compared to the given reference question. Using SimQG, we showcase the key aspect of QSTS that differentiates it from all existing measures. QSTS is not only able to characterize similarity between two questions, but is also able to score questions with respect to passage contexts. Thus QSTS is, to our knowledge, the first metric that enables the measurement of QG performance in a reference-free manner.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gollapalli-ng-2022-qsts">
<titleInfo>
<title>QSTS: A Question-Sensitive Text Similarity Measure for Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujatha</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Gollapalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">See-Kiong</namePart>
<namePart type="family">Ng</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>While question generation (QG) has received significant focus in conversation modeling and text generation research, the problems of comparing questions and evaluation of QG models have remained inadequately addressed. Indeed, QG models continue to be evaluated using traditional measures such as BLEU, METEOR, and ROUGE scores which were designed for other text generation problems. We propose QSTS, a novel Question-Sensitive Text Similarity measure for comparing two questions by characterizing their target intent based on question class, named-entity, and semantic similarity information from the two questions. We show that QSTS addresses several shortcomings of existing measures that depend on n-gram overlap scores and obtains superior results compared to traditional measures on publicly-available QG datasets. We also collect a novel dataset SimQG, for enabling question similarity research in QG contexts. SimQG contains questions generated by state-of-the-art QG models along with human judgements on their relevance with respect to the passage context they were generated for as well as when compared to the given reference question. Using SimQG, we showcase the key aspect of QSTS that differentiates it from all existing measures. QSTS is not only able to characterize similarity between two questions, but is also able to score questions with respect to passage contexts. Thus QSTS is, to our knowledge, the first metric that enables the measurement of QG performance in a reference-free manner.</abstract>
<identifier type="citekey">gollapalli-ng-2022-qsts</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.337</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3835</start>
<end>3846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QSTS: A Question-Sensitive Text Similarity Measure for Question Generation
%A Gollapalli, Sujatha Das
%A Ng, See-Kiong
%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 gollapalli-ng-2022-qsts
%X While question generation (QG) has received significant focus in conversation modeling and text generation research, the problems of comparing questions and evaluation of QG models have remained inadequately addressed. Indeed, QG models continue to be evaluated using traditional measures such as BLEU, METEOR, and ROUGE scores which were designed for other text generation problems. We propose QSTS, a novel Question-Sensitive Text Similarity measure for comparing two questions by characterizing their target intent based on question class, named-entity, and semantic similarity information from the two questions. We show that QSTS addresses several shortcomings of existing measures that depend on n-gram overlap scores and obtains superior results compared to traditional measures on publicly-available QG datasets. We also collect a novel dataset SimQG, for enabling question similarity research in QG contexts. SimQG contains questions generated by state-of-the-art QG models along with human judgements on their relevance with respect to the passage context they were generated for as well as when compared to the given reference question. Using SimQG, we showcase the key aspect of QSTS that differentiates it from all existing measures. QSTS is not only able to characterize similarity between two questions, but is also able to score questions with respect to passage contexts. Thus QSTS is, to our knowledge, the first metric that enables the measurement of QG performance in a reference-free manner.
%U https://aclanthology.org/2022.coling-1.337
%P 3835-3846
Markdown (Informal)
[QSTS: A Question-Sensitive Text Similarity Measure for Question Generation](https://aclanthology.org/2022.coling-1.337) (Gollapalli & Ng, COLING 2022)
ACL