@inproceedings{kottur-moon-2023-overview,
title = "Overview of Situated and Interactive Multimodal Conversations ({SIMMC}) 2.1 Track at {DSTC} 11",
author = "Kottur, Satwik and
Moon, Seungwhan",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.26",
pages = "235--241",
abstract = "With ever increasing interest in task-oriented dialog systems, the recent work on Situated and Interactive Multimodal Conversations (SIMMC 2.0) aims to develop personal assistants that interact with users, grounded in an immersive and co-observed setting of photo-realistic scenes. The dataset contains $11k$ task-oriented dialogs set in an interactive shopping scenario, spanning more than $117k$ utterances. In order to push research towards this next generation virtual assistants, the SIMMC 2.1 challenge was conducted at the Eleventh Dialog System Technology Challenge (DSTC) which had entries from across the world competing to achieve the state-of-the-art performance in the SIMMC 2.1 task. In this report, we present and compare 13 SIMMC 2.1 model entries from 5 trams across the world to understand the current progress made across the last three years (starting with SIMMC 1.0 and 2.0 challenges) for multimodal task-oriented dialog systems. We hope that our analysis throws light on components that showed promise in addition to identifying the gaps for future research towards this grand goal of an immersive multimodal conversational agent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kottur-moon-2023-overview">
<titleInfo>
<title>Overview of Situated and Interactive Multimodal Conversations (SIMMC) 2.1 Track at DSTC 11</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">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With ever increasing interest in task-oriented dialog systems, the recent work on Situated and Interactive Multimodal Conversations (SIMMC 2.0) aims to develop personal assistants that interact with users, grounded in an immersive and co-observed setting of photo-realistic scenes. The dataset contains 11k task-oriented dialogs set in an interactive shopping scenario, spanning more than 117k utterances. In order to push research towards this next generation virtual assistants, the SIMMC 2.1 challenge was conducted at the Eleventh Dialog System Technology Challenge (DSTC) which had entries from across the world competing to achieve the state-of-the-art performance in the SIMMC 2.1 task. In this report, we present and compare 13 SIMMC 2.1 model entries from 5 trams across the world to understand the current progress made across the last three years (starting with SIMMC 1.0 and 2.0 challenges) for multimodal task-oriented dialog systems. We hope that our analysis throws light on components that showed promise in addition to identifying the gaps for future research towards this grand goal of an immersive multimodal conversational agent.</abstract>
<identifier type="citekey">kottur-moon-2023-overview</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.26</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>235</start>
<end>241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of Situated and Interactive Multimodal Conversations (SIMMC) 2.1 Track at DSTC 11
%A Kottur, Satwik
%A Moon, Seungwhan
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F kottur-moon-2023-overview
%X With ever increasing interest in task-oriented dialog systems, the recent work on Situated and Interactive Multimodal Conversations (SIMMC 2.0) aims to develop personal assistants that interact with users, grounded in an immersive and co-observed setting of photo-realistic scenes. The dataset contains 11k task-oriented dialogs set in an interactive shopping scenario, spanning more than 117k utterances. In order to push research towards this next generation virtual assistants, the SIMMC 2.1 challenge was conducted at the Eleventh Dialog System Technology Challenge (DSTC) which had entries from across the world competing to achieve the state-of-the-art performance in the SIMMC 2.1 task. In this report, we present and compare 13 SIMMC 2.1 model entries from 5 trams across the world to understand the current progress made across the last three years (starting with SIMMC 1.0 and 2.0 challenges) for multimodal task-oriented dialog systems. We hope that our analysis throws light on components that showed promise in addition to identifying the gaps for future research towards this grand goal of an immersive multimodal conversational agent.
%U https://aclanthology.org/2023.dstc-1.26
%P 235-241
Markdown (Informal)
[Overview of Situated and Interactive Multimodal Conversations (SIMMC) 2.1 Track at DSTC 11](https://aclanthology.org/2023.dstc-1.26) (Kottur & Moon, DSTC-WS 2023)
ACL