@inproceedings{taslimi-etal-2025-extracting,
title = "Extracting, Detecting, and Generating Research Questions for Scientific Articles",
author = "Taslimi, Sina and
Capari, Artemis and
Azarbonyad, Hosein and
Zhu, Zi Long and
Afzal, Zubair and
Kanoulas, Evangelos and
Tsatsaronis, George",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.573/",
pages = "8573--8588",
abstract = "The volume of academic articles is increasing rapidly, reflecting the growing emphasis on research and scholarship across different science disciplines. This rapid growth necessitates the development of tools for more efficient and rapid understanding of these articles. Clear and well-defined Research Questions (RQs) in research articles can help guide scholarly inquiries. However, many academic studies lack a proper definition of RQs in their articles. This research addresses this gap by presenting a comprehensive framework for the systematic extraction, detection, and generation of RQs from scientific articles. The extraction component uses a set of regular expressions to identify articles containing well-defined RQs. The detection component aims to identify more complex RQs in articles, beyond those captured by the rule-based extraction method. The RQ generation focuses on creating RQs for articles that lack them. We integrate all these components to build a pipeline to extract RQs or generate them based on the articles' full text. We evaluate the performance of the designed pipeline on a set of metrics designed to assess the quality of RQs. Our results indicate that the proposed pipeline can reliably detect RQs and generate high-quality ones."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taslimi-etal-2025-extracting">
<titleInfo>
<title>Extracting, Detecting, and Generating Research Questions for Scientific Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Taslimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artemis</namePart>
<namePart type="family">Capari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Azarbonyad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zi</namePart>
<namePart type="given">Long</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zubair</namePart>
<namePart type="family">Afzal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evangelos</namePart>
<namePart type="family">Kanoulas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Tsatsaronis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The volume of academic articles is increasing rapidly, reflecting the growing emphasis on research and scholarship across different science disciplines. This rapid growth necessitates the development of tools for more efficient and rapid understanding of these articles. Clear and well-defined Research Questions (RQs) in research articles can help guide scholarly inquiries. However, many academic studies lack a proper definition of RQs in their articles. This research addresses this gap by presenting a comprehensive framework for the systematic extraction, detection, and generation of RQs from scientific articles. The extraction component uses a set of regular expressions to identify articles containing well-defined RQs. The detection component aims to identify more complex RQs in articles, beyond those captured by the rule-based extraction method. The RQ generation focuses on creating RQs for articles that lack them. We integrate all these components to build a pipeline to extract RQs or generate them based on the articles’ full text. We evaluate the performance of the designed pipeline on a set of metrics designed to assess the quality of RQs. Our results indicate that the proposed pipeline can reliably detect RQs and generate high-quality ones.</abstract>
<identifier type="citekey">taslimi-etal-2025-extracting</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.573/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8573</start>
<end>8588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting, Detecting, and Generating Research Questions for Scientific Articles
%A Taslimi, Sina
%A Capari, Artemis
%A Azarbonyad, Hosein
%A Zhu, Zi Long
%A Afzal, Zubair
%A Kanoulas, Evangelos
%A Tsatsaronis, George
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F taslimi-etal-2025-extracting
%X The volume of academic articles is increasing rapidly, reflecting the growing emphasis on research and scholarship across different science disciplines. This rapid growth necessitates the development of tools for more efficient and rapid understanding of these articles. Clear and well-defined Research Questions (RQs) in research articles can help guide scholarly inquiries. However, many academic studies lack a proper definition of RQs in their articles. This research addresses this gap by presenting a comprehensive framework for the systematic extraction, detection, and generation of RQs from scientific articles. The extraction component uses a set of regular expressions to identify articles containing well-defined RQs. The detection component aims to identify more complex RQs in articles, beyond those captured by the rule-based extraction method. The RQ generation focuses on creating RQs for articles that lack them. We integrate all these components to build a pipeline to extract RQs or generate them based on the articles’ full text. We evaluate the performance of the designed pipeline on a set of metrics designed to assess the quality of RQs. Our results indicate that the proposed pipeline can reliably detect RQs and generate high-quality ones.
%U https://aclanthology.org/2025.coling-main.573/
%P 8573-8588
Markdown (Informal)
[Extracting, Detecting, and Generating Research Questions for Scientific Articles](https://aclanthology.org/2025.coling-main.573/) (Taslimi et al., COLING 2025)
ACL
- Sina Taslimi, Artemis Capari, Hosein Azarbonyad, Zi Long Zhu, Zubair Afzal, Evangelos Kanoulas, and George Tsatsaronis. 2025. Extracting, Detecting, and Generating Research Questions for Scientific Articles. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8573–8588, Abu Dhabi, UAE. Association for Computational Linguistics.