@inproceedings{moon-etal-2020-situated,
title = "Situated and Interactive Multimodal Conversations",
author = "Moon, Seungwhan and
Kottur, Satwik and
Crook, Paul and
De, Ankita and
Poddar, Shivani and
Levin, Theodore and
Whitney, David and
Difranco, Daniel and
Beirami, Ahmad and
Cho, Eunjoon and
Subba, Rajen and
Geramifard, Alborz",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.96",
doi = "10.18653/v1/2020.coling-main.96",
pages = "1103--1121",
abstract = "Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, and the user{'}s utterances), and perform multimodal actions (, displaying a route while generating the system{'}s utterance). We introduce Situated Interactive MultiModal Conversations (SIMMC) as a new direction aimed at training agents that take multimodal actions grounded in a co-evolving multimodal input context in addition to the dialog history. We provide two SIMMC datasets totalling {\textasciitilde}13K human-human dialogs ({\textasciitilde}169K utterances) collected using a multimodal Wizard-of-Oz (WoZ) setup, on two shopping domains: (a) furniture {--} grounded in a shared virtual environment; and (b) fashion {--} grounded in an evolving set of images. Datasets include multimodal context of the items appearing in each scene, and contextual NLU, NLG and coreference annotations using a novel and unified framework of SIMMC conversational acts for both user and assistant utterances. Finally, we present several tasks within SIMMC as objective evaluation protocols, such as structural API prediction, response generation, and dialog state tracking. We benchmark a collection of existing models on these SIMMC tasks as strong baselines, and demonstrate rich multimodal conversational interactions. Our data, annotations, and models will be made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moon-etal-2020-situated">
<titleInfo>
<title>Situated and Interactive Multimodal Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</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">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">De</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivani</namePart>
<namePart type="family">Poddar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodore</namePart>
<namePart type="family">Levin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Whitney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Difranco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Beirami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunjoon</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Subba</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>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, and the user’s utterances), and perform multimodal actions (, displaying a route while generating the system’s utterance). We introduce Situated Interactive MultiModal Conversations (SIMMC) as a new direction aimed at training agents that take multimodal actions grounded in a co-evolving multimodal input context in addition to the dialog history. We provide two SIMMC datasets totalling ~13K human-human dialogs (~169K utterances) collected using a multimodal Wizard-of-Oz (WoZ) setup, on two shopping domains: (a) furniture – grounded in a shared virtual environment; and (b) fashion – grounded in an evolving set of images. Datasets include multimodal context of the items appearing in each scene, and contextual NLU, NLG and coreference annotations using a novel and unified framework of SIMMC conversational acts for both user and assistant utterances. Finally, we present several tasks within SIMMC as objective evaluation protocols, such as structural API prediction, response generation, and dialog state tracking. We benchmark a collection of existing models on these SIMMC tasks as strong baselines, and demonstrate rich multimodal conversational interactions. Our data, annotations, and models will be made publicly available.</abstract>
<identifier type="citekey">moon-etal-2020-situated</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.96</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.96</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1103</start>
<end>1121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Situated and Interactive Multimodal Conversations
%A Moon, Seungwhan
%A Kottur, Satwik
%A Crook, Paul
%A De, Ankita
%A Poddar, Shivani
%A Levin, Theodore
%A Whitney, David
%A Difranco, Daniel
%A Beirami, Ahmad
%A Cho, Eunjoon
%A Subba, Rajen
%A Geramifard, Alborz
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F moon-etal-2020-situated
%X Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, and the user’s utterances), and perform multimodal actions (, displaying a route while generating the system’s utterance). We introduce Situated Interactive MultiModal Conversations (SIMMC) as a new direction aimed at training agents that take multimodal actions grounded in a co-evolving multimodal input context in addition to the dialog history. We provide two SIMMC datasets totalling ~13K human-human dialogs (~169K utterances) collected using a multimodal Wizard-of-Oz (WoZ) setup, on two shopping domains: (a) furniture – grounded in a shared virtual environment; and (b) fashion – grounded in an evolving set of images. Datasets include multimodal context of the items appearing in each scene, and contextual NLU, NLG and coreference annotations using a novel and unified framework of SIMMC conversational acts for both user and assistant utterances. Finally, we present several tasks within SIMMC as objective evaluation protocols, such as structural API prediction, response generation, and dialog state tracking. We benchmark a collection of existing models on these SIMMC tasks as strong baselines, and demonstrate rich multimodal conversational interactions. Our data, annotations, and models will be made publicly available.
%R 10.18653/v1/2020.coling-main.96
%U https://aclanthology.org/2020.coling-main.96
%U https://doi.org/10.18653/v1/2020.coling-main.96
%P 1103-1121
Markdown (Informal)
[Situated and Interactive Multimodal Conversations](https://aclanthology.org/2020.coling-main.96) (Moon et al., COLING 2020)
ACL
- Seungwhan Moon, Satwik Kottur, Paul Crook, Ankita De, Shivani Poddar, Theodore Levin, David Whitney, Daniel Difranco, Ahmad Beirami, Eunjoon Cho, Rajen Subba, and Alborz Geramifard. 2020. Situated and Interactive Multimodal Conversations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1103–1121, Barcelona, Spain (Online). International Committee on Computational Linguistics.