@inproceedings{wu-etal-2023-simmc,
title = "{SIMMC}-{VR}: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive {VR} Streams",
author = "Wu, Te-Lin and
Kottur, Satwik and
Madotto, Andrea and
Azab, Mahmoud and
Rodriguez, Pedro and
Damavandi, Babak and
Peng, Nanyun and
Moon, Seungwhan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.345",
doi = "10.18653/v1/2023.acl-long.345",
pages = "6273--6291",
abstract = "Building an AI assistant that can seamlessly converse and instruct humans, in a user-centric situated scenario, requires several essential abilities:(1) spatial and temporal understanding of the situated and real-time user scenes,(2) capability of grounding the actively perceived visuals of users to conversation contexts,and (3) conversational reasoning over past utterances to perform just-in-time assistance. However, we currently lack a large-scale benchmark that captures user{--}assistant interactions with all of the aforementioned features. To this end, we propose SIMMC-VR, an extension of the SIMMC-2.0 dataset, to a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR.We propose a novel data collection paradigm that involves(1) generating object-centric multimodal dialog flows with egocentric visual streams and visually-grounded templates,and (2) manually paraphrasing the simulated dialogs for naturalness and diversity while preserving multimodal dependencies. To measure meaningful progress in the field, we propose four tasks to address the new challenges in SIMMC-VR, which require complex spatial-temporal dialog reasoning in active egocentric scenes. We benchmark the proposed tasks with strong multimodal models, and highlight the key capabilities that current models lack for future research directions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-simmc">
<titleInfo>
<title>SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Te-Lin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Azab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Babak</namePart>
<namePart type="family">Damavandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</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>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building an AI assistant that can seamlessly converse and instruct humans, in a user-centric situated scenario, requires several essential abilities:(1) spatial and temporal understanding of the situated and real-time user scenes,(2) capability of grounding the actively perceived visuals of users to conversation contexts,and (3) conversational reasoning over past utterances to perform just-in-time assistance. However, we currently lack a large-scale benchmark that captures user–assistant interactions with all of the aforementioned features. To this end, we propose SIMMC-VR, an extension of the SIMMC-2.0 dataset, to a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR.We propose a novel data collection paradigm that involves(1) generating object-centric multimodal dialog flows with egocentric visual streams and visually-grounded templates,and (2) manually paraphrasing the simulated dialogs for naturalness and diversity while preserving multimodal dependencies. To measure meaningful progress in the field, we propose four tasks to address the new challenges in SIMMC-VR, which require complex spatial-temporal dialog reasoning in active egocentric scenes. We benchmark the proposed tasks with strong multimodal models, and highlight the key capabilities that current models lack for future research directions.</abstract>
<identifier type="citekey">wu-etal-2023-simmc</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.345</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.345</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6273</start>
<end>6291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams
%A Wu, Te-Lin
%A Kottur, Satwik
%A Madotto, Andrea
%A Azab, Mahmoud
%A Rodriguez, Pedro
%A Damavandi, Babak
%A Peng, Nanyun
%A Moon, Seungwhan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wu-etal-2023-simmc
%X Building an AI assistant that can seamlessly converse and instruct humans, in a user-centric situated scenario, requires several essential abilities:(1) spatial and temporal understanding of the situated and real-time user scenes,(2) capability of grounding the actively perceived visuals of users to conversation contexts,and (3) conversational reasoning over past utterances to perform just-in-time assistance. However, we currently lack a large-scale benchmark that captures user–assistant interactions with all of the aforementioned features. To this end, we propose SIMMC-VR, an extension of the SIMMC-2.0 dataset, to a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR.We propose a novel data collection paradigm that involves(1) generating object-centric multimodal dialog flows with egocentric visual streams and visually-grounded templates,and (2) manually paraphrasing the simulated dialogs for naturalness and diversity while preserving multimodal dependencies. To measure meaningful progress in the field, we propose four tasks to address the new challenges in SIMMC-VR, which require complex spatial-temporal dialog reasoning in active egocentric scenes. We benchmark the proposed tasks with strong multimodal models, and highlight the key capabilities that current models lack for future research directions.
%R 10.18653/v1/2023.acl-long.345
%U https://aclanthology.org/2023.acl-long.345
%U https://doi.org/10.18653/v1/2023.acl-long.345
%P 6273-6291
Markdown (Informal)
[SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams](https://aclanthology.org/2023.acl-long.345) (Wu et al., ACL 2023)
ACL
- Te-Lin Wu, Satwik Kottur, Andrea Madotto, Mahmoud Azab, Pedro Rodriguez, Babak Damavandi, Nanyun Peng, and Seungwhan Moon. 2023. SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6273–6291, Toronto, Canada. Association for Computational Linguistics.