<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="willemsen-skantze-2024-referring-expression">
    <titleInfo>
        <title>Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bram</namePart>
        <namePart type="family">Willemsen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gabriel</namePart>
        <namePart type="family">Skantze</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Natural Language Generation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Mahamood</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nguyen</namePart>
            <namePart type="given">Le</namePart>
            <namePart type="family">Minh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daphne</namePart>
            <namePart type="family">Ippolito</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method constitutes a two-stage process. First, we model REG as a text- and image-conditioned next-token prediction task. REs are autoregressively generated based on their preceding linguistic context and a visual representation of the referent. Second, we propose the use of discourse-aware comprehension guiding as part of a generate-and-rerank strategy through which candidate REs generated with our REG model are reranked based on their discourse-dependent discriminatory power. Results from our human evaluation indicate that our proposed two-stage approach is effective in producing discriminative REs, with higher performance in terms of text-image retrieval accuracy for reranked REs compared to those generated using greedy decoding.</abstract>
    <identifier type="citekey">willemsen-skantze-2024-referring-expression</identifier>
    <location>
        <url>https://aclanthology.org/2024.inlg-main.38</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>453</start>
            <end>469</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding
%A Willemsen, Bram
%A Skantze, Gabriel
%Y Mahamood, Saad
%Y Minh, Nguyen Le
%Y Ippolito, Daphne
%S Proceedings of the 17th International Natural Language Generation Conference
%D 2024
%8 September
%I Association for Computational Linguistics
%C Tokyo, Japan
%F willemsen-skantze-2024-referring-expression
%X We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method constitutes a two-stage process. First, we model REG as a text- and image-conditioned next-token prediction task. REs are autoregressively generated based on their preceding linguistic context and a visual representation of the referent. Second, we propose the use of discourse-aware comprehension guiding as part of a generate-and-rerank strategy through which candidate REs generated with our REG model are reranked based on their discourse-dependent discriminatory power. Results from our human evaluation indicate that our proposed two-stage approach is effective in producing discriminative REs, with higher performance in terms of text-image retrieval accuracy for reranked REs compared to those generated using greedy decoding.
%U https://aclanthology.org/2024.inlg-main.38
%P 453-469

Markdown (Informal)

[Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding](https://aclanthology.org/2024.inlg-main.38) (Willemsen & Skantze, INLG 2024)

• Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding (Willemsen & Skantze, INLG 2024)

ACL

• Bram Willemsen and Gabriel Skantze. 2024. Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding. In Proceedings of the 17th International Natural Language Generation Conference, pages 453–469, Tokyo, Japan. Association for Computational Linguistics.