<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2021-reasoning-visual">
    <titleInfo>
        <title>Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gi-Cheon</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junseok</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwaran</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Byoung-Tak</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jin-Hwa</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic structures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.</abstract>
    <identifier type="citekey">kang-etal-2021-reasoning-visual</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.31</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.31</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>327</start>
            <end>339</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer
%A Kang, Gi-Cheon
%A Park, Junseok
%A Lee, Hwaran
%A Zhang, Byoung-Tak
%A Kim, Jin-Hwa
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F kang-etal-2021-reasoning-visual
%X Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic structures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.
%R 10.18653/v1/2021.findings-emnlp.31
%U https://aclanthology.org/2021.findings-emnlp.31
%U https://doi.org/10.18653/v1/2021.findings-emnlp.31
%P 327-339

Markdown (Informal)

[Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer](https://aclanthology.org/2021.findings-emnlp.31) (Kang et al., Findings 2021)

• Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer (Kang et al., Findings 2021)

ACL

• Gi-Cheon Kang, Junseok Park, Hwaran Lee, Byoung-Tak Zhang, and Jin-Hwa Kim. 2021. Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 327–339, Punta Cana, Dominican Republic. Association for Computational Linguistics.