@inproceedings{chang-etal-2023-contrastively,
title = "Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal {TOD} Systems",
author = "Chang, Youngjae and
Young Kim, Doo and
Kim, Jinyoung and
Kim, Keunha and
Cha, Hyunmook and
Min, Suyoung and
Ko, Youngjoong and
Lee, Kye-Hwan and
Park, Joonwoo",
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-1.4",
pages = "25--30",
abstract = "The Situated Interactive MultiModal Conversations (SIMMC2.1) Challenge 2022 is hosted by the Eleventh Dialog System Technology Challenge (DSTC11). This is the third consecutive year multimodal dialog systems have been selected as an official track of the competition, promoted by the continued interest in the research community. The task of SIMMC is to create a shopping assistant agent that can communicate with customers in a virtual store. It requires processing store scenes and product catalogs along with the customer{'}s request. The task is decomposed into four steps and each becomes a subtask. In this work, we explore the common approaches to modeling multimodality and find the method with the most potential. We also identify a discrepancy in using pretrained language models for dialog tasks and devise a simple domain-adaptation method. Our model came in third place for object coreferencing, dialog state tracking, and response generation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2023-contrastively">
<titleInfo>
<title>Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal TOD Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youngjae</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doo</namePart>
<namePart type="family">Young Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinyoung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keunha</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunmook</namePart>
<namePart type="family">Cha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suyoung</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngjoong</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kye-Hwan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonwoo</namePart>
<namePart type="family">Park</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>The Situated Interactive MultiModal Conversations (SIMMC2.1) Challenge 2022 is hosted by the Eleventh Dialog System Technology Challenge (DSTC11). This is the third consecutive year multimodal dialog systems have been selected as an official track of the competition, promoted by the continued interest in the research community. The task of SIMMC is to create a shopping assistant agent that can communicate with customers in a virtual store. It requires processing store scenes and product catalogs along with the customer’s request. The task is decomposed into four steps and each becomes a subtask. In this work, we explore the common approaches to modeling multimodality and find the method with the most potential. We also identify a discrepancy in using pretrained language models for dialog tasks and devise a simple domain-adaptation method. Our model came in third place for object coreferencing, dialog state tracking, and response generation tasks.</abstract>
<identifier type="citekey">chang-etal-2023-contrastively</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.4</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal TOD Systems
%A Chang, Youngjae
%A Young Kim, Doo
%A Kim, Jinyoung
%A Kim, Keunha
%A Cha, Hyunmook
%A Min, Suyoung
%A Ko, Youngjoong
%A Lee, Kye-Hwan
%A Park, Joonwoo
%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 chang-etal-2023-contrastively
%X The Situated Interactive MultiModal Conversations (SIMMC2.1) Challenge 2022 is hosted by the Eleventh Dialog System Technology Challenge (DSTC11). This is the third consecutive year multimodal dialog systems have been selected as an official track of the competition, promoted by the continued interest in the research community. The task of SIMMC is to create a shopping assistant agent that can communicate with customers in a virtual store. It requires processing store scenes and product catalogs along with the customer’s request. The task is decomposed into four steps and each becomes a subtask. In this work, we explore the common approaches to modeling multimodality and find the method with the most potential. We also identify a discrepancy in using pretrained language models for dialog tasks and devise a simple domain-adaptation method. Our model came in third place for object coreferencing, dialog state tracking, and response generation tasks.
%U https://aclanthology.org/2023.dstc-1.4
%P 25-30
Markdown (Informal)
[Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal TOD Systems](https://aclanthology.org/2023.dstc-1.4) (Chang et al., DSTC-WS 2023)
ACL
- Youngjae Chang, Doo Young Kim, Jinyoung Kim, Keunha Kim, Hyunmook Cha, Suyoung Min, Youngjoong Ko, Kye-Hwan Lee, and Joonwoo Park. 2023. Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal TOD Systems. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 25–30, Prague, Czech Republic. Association for Computational Linguistics.