@inproceedings{zhan-etal-2024-going,
title = "Going beyond Imagination! Enhancing Multi-modal Dialogue Agents with Synthetic Visual Descriptions",
author = "Zhan, Haolan and
Maruf, Sameen and
Zukerman, Ingrid and
Haffari, Gholamreza",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.36",
pages = "420--427",
abstract = "Building a dialogue agent that can seamlessly interact with humans in multi-modal regimes, requires two fundamental abilities: (1) understanding emotion and dialogue acts within situated user scenarios, and (2) grounding perceived visual cues to dialogue contexts. However, recent works have uncovered shortcomings of existing dialogue agents in understanding emotions and dialogue acts, and in ground- ing visual cues effectively. In this work, we investigate whether additional dialogue data with only visual descriptions can help dialogue agents effectively align visual and textual features, and enhance the ability of dialogue agents to ground perceived visual cues to dialogue contexts. To this end, in the absence of a suitable dataset, we propose a synthetic visual description generation pipeline, and con- tribute a large-scale synthetic visual description dataset. In addition, we propose a general training procedure for effectively leveraging these synthetic data. We conduct comprehensive analyses to evaluate the impact of synthetic data on two benchmarks: MELD and IEMOCAP. Our findings suggest that synthetic visual descriptions can serve as an effective way to enhance a dialogue agents{'} grounding ability, and that the training scheme affects the extent to which these descriptions improve the agent{'}s performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhan-etal-2024-going">
<titleInfo>
<title>Going beyond Imagination! Enhancing Multi-modal Dialogue Agents with Synthetic Visual Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haolan</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameen</namePart>
<namePart type="family">Maruf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</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 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building a dialogue agent that can seamlessly interact with humans in multi-modal regimes, requires two fundamental abilities: (1) understanding emotion and dialogue acts within situated user scenarios, and (2) grounding perceived visual cues to dialogue contexts. However, recent works have uncovered shortcomings of existing dialogue agents in understanding emotions and dialogue acts, and in ground- ing visual cues effectively. In this work, we investigate whether additional dialogue data with only visual descriptions can help dialogue agents effectively align visual and textual features, and enhance the ability of dialogue agents to ground perceived visual cues to dialogue contexts. To this end, in the absence of a suitable dataset, we propose a synthetic visual description generation pipeline, and con- tribute a large-scale synthetic visual description dataset. In addition, we propose a general training procedure for effectively leveraging these synthetic data. We conduct comprehensive analyses to evaluate the impact of synthetic data on two benchmarks: MELD and IEMOCAP. Our findings suggest that synthetic visual descriptions can serve as an effective way to enhance a dialogue agents’ grounding ability, and that the training scheme affects the extent to which these descriptions improve the agent’s performance.</abstract>
<identifier type="citekey">zhan-etal-2024-going</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.36</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>420</start>
<end>427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Going beyond Imagination! Enhancing Multi-modal Dialogue Agents with Synthetic Visual Descriptions
%A Zhan, Haolan
%A Maruf, Sameen
%A Zukerman, Ingrid
%A Haffari, Gholamreza
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F zhan-etal-2024-going
%X Building a dialogue agent that can seamlessly interact with humans in multi-modal regimes, requires two fundamental abilities: (1) understanding emotion and dialogue acts within situated user scenarios, and (2) grounding perceived visual cues to dialogue contexts. However, recent works have uncovered shortcomings of existing dialogue agents in understanding emotions and dialogue acts, and in ground- ing visual cues effectively. In this work, we investigate whether additional dialogue data with only visual descriptions can help dialogue agents effectively align visual and textual features, and enhance the ability of dialogue agents to ground perceived visual cues to dialogue contexts. To this end, in the absence of a suitable dataset, we propose a synthetic visual description generation pipeline, and con- tribute a large-scale synthetic visual description dataset. In addition, we propose a general training procedure for effectively leveraging these synthetic data. We conduct comprehensive analyses to evaluate the impact of synthetic data on two benchmarks: MELD and IEMOCAP. Our findings suggest that synthetic visual descriptions can serve as an effective way to enhance a dialogue agents’ grounding ability, and that the training scheme affects the extent to which these descriptions improve the agent’s performance.
%U https://aclanthology.org/2024.sigdial-1.36
%P 420-427
Markdown (Informal)
[Going beyond Imagination! Enhancing Multi-modal Dialogue Agents with Synthetic Visual Descriptions](https://aclanthology.org/2024.sigdial-1.36) (Zhan et al., SIGDIAL 2024)
ACL