<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kottur-etal-2021-dialogstitch">
    <titleInfo>
        <title>DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Satwik</namePart>
        <namePart type="family">Kottur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chinnadhurai</namePart>
        <namePart type="family">Sankar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alborz</namePart>
        <namePart type="family">Geramifard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore and Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Real-world conversational agents must effectively handle long conversations that span multiple contexts. Such context can be interspersed with chitchat (dialog turns not directly related to the task at hand), and potentially grounded in a multimodal setting. While prior work focused on the above aspects in isolation, there is a lack of a unified framework that studies them together. To overcome this, we propose DialogStitch, a novel framework to seamlessly ‘stitch’ multiple conversations and highlight these desirable traits in a taskoriented dialog. After stitching, our dialogs are provably deeper, contain longer-term dependencies, and span multiple contexts, when compared with the source dialogs—all free of cost without any additional annotations! Though our framework generalizes to a variety of combinations, we demonstrate its benefits in two settings: (a) multimodal, imagegrounded conversations, and, (b) task-oriented dialogs fused with chit-chat conversations. We benchmark state-of-the-art dialog models on our datasets and find accuracy drops of (a) 12% and (b) 45% respectively, indicating the additional challenges in the stitched dialogs. Our code and data are publicly available.</abstract>
    <identifier type="citekey">kottur-etal-2021-dialogstitch</identifier>
    <location>
        <url>https://aclanthology.org/2021.sigdial-1.3</url>
    </location>
    <part>
        <date>2021-jul</date>
        <extent unit="page">
            <start>21</start>
            <end>26</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs
%A Kottur, Satwik
%A Sankar, Chinnadhurai
%A Yu, Zhou
%A Geramifard, Alborz
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 jul
%I Association for Computational Linguistics
%C Singapore and Online
%F kottur-etal-2021-dialogstitch
%X Real-world conversational agents must effectively handle long conversations that span multiple contexts. Such context can be interspersed with chitchat (dialog turns not directly related to the task at hand), and potentially grounded in a multimodal setting. While prior work focused on the above aspects in isolation, there is a lack of a unified framework that studies them together. To overcome this, we propose DialogStitch, a novel framework to seamlessly ‘stitch’ multiple conversations and highlight these desirable traits in a taskoriented dialog. After stitching, our dialogs are provably deeper, contain longer-term dependencies, and span multiple contexts, when compared with the source dialogs—all free of cost without any additional annotations! Though our framework generalizes to a variety of combinations, we demonstrate its benefits in two settings: (a) multimodal, imagegrounded conversations, and, (b) task-oriented dialogs fused with chit-chat conversations. We benchmark state-of-the-art dialog models on our datasets and find accuracy drops of (a) 12% and (b) 45% respectively, indicating the additional challenges in the stitched dialogs. Our code and data are publicly available.
%U https://aclanthology.org/2021.sigdial-1.3
%P 21-26

Markdown (Informal)

[DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs](https://aclanthology.org/2021.sigdial-1.3) (Kottur et al., SIGDIAL 2021)

• DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs (Kottur et al., SIGDIAL 2021)

ACL

• Satwik Kottur, Chinnadhurai Sankar, Zhou Yu, and Alborz Geramifard. 2021. DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 21–26, Singapore and Online. Association for Computational Linguistics.