@inproceedings{lei-etal-2024-qsnail-questionnaire,
title = "Qsnail: A Questionnaire Dataset for Sequential Question Generation",
author = "Lei, Yan and
Pang, Liang and
Wang, Yuanzhuo and
Shen, Huawei and
Cheng, Xueqi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1174",
pages = "13407--13418",
abstract = "The questionnaire is a professional research methodology used for both qualitative and quantitative analysis of human opinions, preferences, attitudes, and behaviors. However, designing and evaluating questionnaires demands significant effort due to their intricate and complex structure. Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure. Specifically, the questions should be relevant and specific to the given research topic and intent. The options should be tailored to the questions, ensuring they are mutually exclusive, completed, and ordered sensibly. Moreover, the sequence of questions should follow a logical order, grouping similar topics together. As a result, automatically generating questionnaires presents a significant challenge and this area has received limited attention primarily due to the scarcity of high-quality datasets. To address these issues, we present Qsnail, the first dataset specifically constructed for the questionnaire generation task, which comprises 13,168 human-written questionnaires gathered from online platforms. We further conduct experiments on Qsnail, and the results reveal that retrieval models and traditional generative models do not fully align with the given research topic and intents. Large language models, while more closely related to the research topic and intents, exhibit significant limitations in terms of diversity and specificity. Despite enhancements through the chain-of-thought prompt and finetuning, questionnaires generated by language models still fall short of human-written questionnaires. Therefore, questionnaire generation is challenging and needs to be further explored. The dataset will be published in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lei-etal-2024-qsnail-questionnaire">
<titleInfo>
<title>Qsnail: A Questionnaire Dataset for Sequential Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanzhuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huawei</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueqi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The questionnaire is a professional research methodology used for both qualitative and quantitative analysis of human opinions, preferences, attitudes, and behaviors. However, designing and evaluating questionnaires demands significant effort due to their intricate and complex structure. Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure. Specifically, the questions should be relevant and specific to the given research topic and intent. The options should be tailored to the questions, ensuring they are mutually exclusive, completed, and ordered sensibly. Moreover, the sequence of questions should follow a logical order, grouping similar topics together. As a result, automatically generating questionnaires presents a significant challenge and this area has received limited attention primarily due to the scarcity of high-quality datasets. To address these issues, we present Qsnail, the first dataset specifically constructed for the questionnaire generation task, which comprises 13,168 human-written questionnaires gathered from online platforms. We further conduct experiments on Qsnail, and the results reveal that retrieval models and traditional generative models do not fully align with the given research topic and intents. Large language models, while more closely related to the research topic and intents, exhibit significant limitations in terms of diversity and specificity. Despite enhancements through the chain-of-thought prompt and finetuning, questionnaires generated by language models still fall short of human-written questionnaires. Therefore, questionnaire generation is challenging and needs to be further explored. The dataset will be published in the future.</abstract>
<identifier type="citekey">lei-etal-2024-qsnail-questionnaire</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1174</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13407</start>
<end>13418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Qsnail: A Questionnaire Dataset for Sequential Question Generation
%A Lei, Yan
%A Pang, Liang
%A Wang, Yuanzhuo
%A Shen, Huawei
%A Cheng, Xueqi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lei-etal-2024-qsnail-questionnaire
%X The questionnaire is a professional research methodology used for both qualitative and quantitative analysis of human opinions, preferences, attitudes, and behaviors. However, designing and evaluating questionnaires demands significant effort due to their intricate and complex structure. Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure. Specifically, the questions should be relevant and specific to the given research topic and intent. The options should be tailored to the questions, ensuring they are mutually exclusive, completed, and ordered sensibly. Moreover, the sequence of questions should follow a logical order, grouping similar topics together. As a result, automatically generating questionnaires presents a significant challenge and this area has received limited attention primarily due to the scarcity of high-quality datasets. To address these issues, we present Qsnail, the first dataset specifically constructed for the questionnaire generation task, which comprises 13,168 human-written questionnaires gathered from online platforms. We further conduct experiments on Qsnail, and the results reveal that retrieval models and traditional generative models do not fully align with the given research topic and intents. Large language models, while more closely related to the research topic and intents, exhibit significant limitations in terms of diversity and specificity. Despite enhancements through the chain-of-thought prompt and finetuning, questionnaires generated by language models still fall short of human-written questionnaires. Therefore, questionnaire generation is challenging and needs to be further explored. The dataset will be published in the future.
%U https://aclanthology.org/2024.lrec-main.1174
%P 13407-13418
Markdown (Informal)
[Qsnail: A Questionnaire Dataset for Sequential Question Generation](https://aclanthology.org/2024.lrec-main.1174) (Lei et al., LREC-COLING 2024)
ACL
- Yan Lei, Liang Pang, Yuanzhuo Wang, Huawei Shen, and Xueqi Cheng. 2024. Qsnail: A Questionnaire Dataset for Sequential Question Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13407–13418, Torino, Italia. ELRA and ICCL.