@inproceedings{bhattacharya-etal-2022-unsupervised,
title = "Unsupervised Generation of Long-form Technical Questions from Textbook Metadata using Structured Templates",
author = "Bhattacharya, Indrajit and
Ghosh, Subhasish and
Kundu, Arpita and
Saini, Pratik and
Nayak, Tapas",
booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.pandl-1.3",
pages = "21--28",
abstract = "We explore the task of generating long-form technical questions from textbooks. Semi-structured metadata of a textbook {---} the table of contents and the index {---} provide rich cues for technical question generation. Existing literature for long-form question generation focuses mostly on reading comprehension assessment, and does not use semi-structured metadata for question generation. We design unsupervised template based algorithms for generating questions based on structural and contextual patterns in the index and ToC. We evaluate our approach on textbooks on diverse subjects and show that our approach generates high quality questions of diverse types. We show that, in comparison, zero-shot question generation using pre-trained LLMs on the same meta-data has much poorer quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharya-etal-2022-unsupervised">
<titleInfo>
<title>Unsupervised Generation of Long-form Technical Questions from Textbook Metadata using Structured Templates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Indrajit</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subhasish</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpita</namePart>
<namePart type="family">Kundu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Saini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tapas</namePart>
<namePart type="family">Nayak</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 First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore the task of generating long-form technical questions from textbooks. Semi-structured metadata of a textbook — the table of contents and the index — provide rich cues for technical question generation. Existing literature for long-form question generation focuses mostly on reading comprehension assessment, and does not use semi-structured metadata for question generation. We design unsupervised template based algorithms for generating questions based on structural and contextual patterns in the index and ToC. We evaluate our approach on textbooks on diverse subjects and show that our approach generates high quality questions of diverse types. We show that, in comparison, zero-shot question generation using pre-trained LLMs on the same meta-data has much poorer quality.</abstract>
<identifier type="citekey">bhattacharya-etal-2022-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2022.pandl-1.3</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>21</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Generation of Long-form Technical Questions from Textbook Metadata using Structured Templates
%A Bhattacharya, Indrajit
%A Ghosh, Subhasish
%A Kundu, Arpita
%A Saini, Pratik
%A Nayak, Tapas
%S Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F bhattacharya-etal-2022-unsupervised
%X We explore the task of generating long-form technical questions from textbooks. Semi-structured metadata of a textbook — the table of contents and the index — provide rich cues for technical question generation. Existing literature for long-form question generation focuses mostly on reading comprehension assessment, and does not use semi-structured metadata for question generation. We design unsupervised template based algorithms for generating questions based on structural and contextual patterns in the index and ToC. We evaluate our approach on textbooks on diverse subjects and show that our approach generates high quality questions of diverse types. We show that, in comparison, zero-shot question generation using pre-trained LLMs on the same meta-data has much poorer quality.
%U https://aclanthology.org/2022.pandl-1.3
%P 21-28
Markdown (Informal)
[Unsupervised Generation of Long-form Technical Questions from Textbook Metadata using Structured Templates](https://aclanthology.org/2022.pandl-1.3) (Bhattacharya et al., PANDL 2022)
ACL