@inproceedings{puranik-etal-2023-protege,
title = "{PROTEGE}: Prompt-based Diverse Question Generation from Web Articles",
author = "Puranik, Vinayak and
Majumder, Anirban and
Chaoji, Vineet",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.362",
doi = "10.18653/v1/2023.findings-emnlp.362",
pages = "5449--5463",
abstract = "Rich and diverse knowledge bases (KB) are foundational building blocks for online knowledge sharing communities such as StackOverflow and Quora, and applications such as conversational assistants (aka chatbots). A popular format for knowledge bases is question-answer pairs (or FAQs), where questions are designed to accurately match a multitude of queries. In this paper, we address the problem of automatic creation of such Q{\&}A-based knowledge bases from domain-specific, long-form textual content (e.g., web articles). Specifically, we consider the problem of question generation, which is the task of generating questions given a paragraph of text as input, with a goal to achieve both diversity and fidelity of the generated questions. Towards this goal we propose PROTEGE, a diverse question generation framework which consists of (1) a novel encoder-decoder based Large Language Model (LLM) architecture which can take a variety of prompts and generate a diverse set of candidate questions, and (2) a hill-climbing algorithm that maximizes a sub-modular objective function to balance diversity with fidelity. Through our experiments on three popular public Q{\&}A datasets, we demonstrate that PROTEGE improves diversity by +16{\%} and fidelity by +8{\%} over diverse beam search and prompt-based baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="puranik-etal-2023-protege">
<titleInfo>
<title>PROTEGE: Prompt-based Diverse Question Generation from Web Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vinayak</namePart>
<namePart type="family">Puranik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirban</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vineet</namePart>
<namePart type="family">Chaoji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Rich and diverse knowledge bases (KB) are foundational building blocks for online knowledge sharing communities such as StackOverflow and Quora, and applications such as conversational assistants (aka chatbots). A popular format for knowledge bases is question-answer pairs (or FAQs), where questions are designed to accurately match a multitude of queries. In this paper, we address the problem of automatic creation of such Q&A-based knowledge bases from domain-specific, long-form textual content (e.g., web articles). Specifically, we consider the problem of question generation, which is the task of generating questions given a paragraph of text as input, with a goal to achieve both diversity and fidelity of the generated questions. Towards this goal we propose PROTEGE, a diverse question generation framework which consists of (1) a novel encoder-decoder based Large Language Model (LLM) architecture which can take a variety of prompts and generate a diverse set of candidate questions, and (2) a hill-climbing algorithm that maximizes a sub-modular objective function to balance diversity with fidelity. Through our experiments on three popular public Q&A datasets, we demonstrate that PROTEGE improves diversity by +16% and fidelity by +8% over diverse beam search and prompt-based baselines.</abstract>
<identifier type="citekey">puranik-etal-2023-protege</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.362</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.362</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5449</start>
<end>5463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PROTEGE: Prompt-based Diverse Question Generation from Web Articles
%A Puranik, Vinayak
%A Majumder, Anirban
%A Chaoji, Vineet
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F puranik-etal-2023-protege
%X Rich and diverse knowledge bases (KB) are foundational building blocks for online knowledge sharing communities such as StackOverflow and Quora, and applications such as conversational assistants (aka chatbots). A popular format for knowledge bases is question-answer pairs (or FAQs), where questions are designed to accurately match a multitude of queries. In this paper, we address the problem of automatic creation of such Q&A-based knowledge bases from domain-specific, long-form textual content (e.g., web articles). Specifically, we consider the problem of question generation, which is the task of generating questions given a paragraph of text as input, with a goal to achieve both diversity and fidelity of the generated questions. Towards this goal we propose PROTEGE, a diverse question generation framework which consists of (1) a novel encoder-decoder based Large Language Model (LLM) architecture which can take a variety of prompts and generate a diverse set of candidate questions, and (2) a hill-climbing algorithm that maximizes a sub-modular objective function to balance diversity with fidelity. Through our experiments on three popular public Q&A datasets, we demonstrate that PROTEGE improves diversity by +16% and fidelity by +8% over diverse beam search and prompt-based baselines.
%R 10.18653/v1/2023.findings-emnlp.362
%U https://aclanthology.org/2023.findings-emnlp.362
%U https://doi.org/10.18653/v1/2023.findings-emnlp.362
%P 5449-5463
Markdown (Informal)
[PROTEGE: Prompt-based Diverse Question Generation from Web Articles](https://aclanthology.org/2023.findings-emnlp.362) (Puranik et al., Findings 2023)
ACL