<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keh-etal-2024-asking">
    <titleInfo>
        <title>Asking More Informative Questions for Grounded Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sedrick</namePart>
        <namePart type="family">Keh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">Chiu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Fried</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>When a model is trying to gather information in an interactive setting, it benefits from asking informative questions. However, in the case of a grounded multi-turn image identification task, previous studies have been constrained to polar yes/no questions (White et al., 2021), limiting how much information the model can gain in a single turn. We present an approach that formulates more informative, open-ended questions. In doing so, we discover that off-the-shelf visual question answering (VQA) models often make presupposition errors, which standard information gain question selection methods fail to account for. To address this issue, we propose a method that can incorporate presupposition handling into both question selection and belief updates. Specifically, we use a two-stage process, where the model first filters out images which are irrelevant to a given question, then updates its beliefs about which image the user intends. Through self-play and human evaluations, we show that our method is successful in asking informative open-ended questions, increasing accuracy over the past state-of-the-art by 14%, while resulting in 48% more efficient games in human evaluations.</abstract>
    <identifier type="citekey">keh-etal-2024-asking</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.276</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>4429</start>
            <end>4442</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Asking More Informative Questions for Grounded Retrieval
%A Keh, Sedrick
%A Chiu, Justin
%A Fried, Daniel
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F keh-etal-2024-asking
%X When a model is trying to gather information in an interactive setting, it benefits from asking informative questions. However, in the case of a grounded multi-turn image identification task, previous studies have been constrained to polar yes/no questions (White et al., 2021), limiting how much information the model can gain in a single turn. We present an approach that formulates more informative, open-ended questions. In doing so, we discover that off-the-shelf visual question answering (VQA) models often make presupposition errors, which standard information gain question selection methods fail to account for. To address this issue, we propose a method that can incorporate presupposition handling into both question selection and belief updates. Specifically, we use a two-stage process, where the model first filters out images which are irrelevant to a given question, then updates its beliefs about which image the user intends. Through self-play and human evaluations, we show that our method is successful in asking informative open-ended questions, increasing accuracy over the past state-of-the-art by 14%, while resulting in 48% more efficient games in human evaluations.
%U https://aclanthology.org/2024.findings-naacl.276
%P 4429-4442

Markdown (Informal)

[Asking More Informative Questions for Grounded Retrieval](https://aclanthology.org/2024.findings-naacl.276) (Keh et al., Findings 2024)

• Asking More Informative Questions for Grounded Retrieval (Keh et al., Findings 2024)

ACL

• Sedrick Keh, Justin Chiu, and Daniel Fried. 2024. Asking More Informative Questions for Grounded Retrieval. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4429–4442, Mexico City, Mexico. Association for Computational Linguistics.