<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maheshwari-etal-2023-open">
    <titleInfo>
        <title>Open-World Factually Consistent Question Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Himanshu</namePart>
        <namePart type="family">Maheshwari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sumit</namePart>
        <namePart type="family">Shekhar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Apoorv</namePart>
        <namePart type="family">Saxena</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Niyati</namePart>
        <namePart type="family">Chhaya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Question generation methods based on pre-trained language models often suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph. Domain shift – where the test data is from a different domain than the training data - further exacerbates the problem of hallucination. This is a critical issue for any natural language application doing question generation. In this work, we propose an effective data processing technique based on de-lexicalization for consistent question generation across domains. Unlike existing approaches for remedying hallucination, the proposed approach does not filter training data and is generic across question-generation models. Experimental results across six benchmark datasets show that our model is robust to domain shift and produces entity-level factually consistent questions without significant impact on traditional metrics.</abstract>
    <identifier type="citekey">maheshwari-etal-2023-open</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.151</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.151</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>2390</start>
            <end>2404</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Open-World Factually Consistent Question Generation
%A Maheshwari, Himanshu
%A Shekhar, Sumit
%A Saxena, Apoorv
%A Chhaya, Niyati
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F maheshwari-etal-2023-open
%X Question generation methods based on pre-trained language models often suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph. Domain shift – where the test data is from a different domain than the training data - further exacerbates the problem of hallucination. This is a critical issue for any natural language application doing question generation. In this work, we propose an effective data processing technique based on de-lexicalization for consistent question generation across domains. Unlike existing approaches for remedying hallucination, the proposed approach does not filter training data and is generic across question-generation models. Experimental results across six benchmark datasets show that our model is robust to domain shift and produces entity-level factually consistent questions without significant impact on traditional metrics.
%R 10.18653/v1/2023.findings-acl.151
%U https://aclanthology.org/2023.findings-acl.151
%U https://doi.org/10.18653/v1/2023.findings-acl.151
%P 2390-2404

Markdown (Informal)

[Open-World Factually Consistent Question Generation](https://aclanthology.org/2023.findings-acl.151) (Maheshwari et al., Findings 2023)

• Open-World Factually Consistent Question Generation (Maheshwari et al., Findings 2023)

ACL

• Himanshu Maheshwari, Sumit Shekhar, Apoorv Saxena, and Niyati Chhaya. 2023. Open-World Factually Consistent Question Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2390–2404, Toronto, Canada. Association for Computational Linguistics.