@inproceedings{long-etal-2023-multimodal,
title = "Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark",
author = "Long, Yuxing and
Hui, Binyuan and
Yuan, Caixia and
Huang, Fei and
Li, Yongbin and
Wang, Xiaojie",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.217",
doi = "10.18653/v1/2023.findings-acl.217",
pages = "3515--3533",
abstract = "Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario. This paper introduces a new dataset SURE (Multimodal Recommendation Dialog with Subjective Preference), which contains 12K shopping dialogs in complex store scenes. The data is built in two phases with human annotations to ensure quality and diversity. SURE is well-annotated with subjective preferences and recommendation acts proposed by sales experts. A comprehensive analysis is given to reveal the distinguishing features of SURE. Three benchmark tasks are then proposed on the data to evaluate the capability of multimodal recommendation agents. Basing on the SURE, we propose a baseline model, powered by a state-of-the-art multimodal model, for these tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2023-multimodal">
<titleInfo>
<title>Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxing</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyuan</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongbin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario. This paper introduces a new dataset SURE (Multimodal Recommendation Dialog with Subjective Preference), which contains 12K shopping dialogs in complex store scenes. The data is built in two phases with human annotations to ensure quality and diversity. SURE is well-annotated with subjective preferences and recommendation acts proposed by sales experts. A comprehensive analysis is given to reveal the distinguishing features of SURE. Three benchmark tasks are then proposed on the data to evaluate the capability of multimodal recommendation agents. Basing on the SURE, we propose a baseline model, powered by a state-of-the-art multimodal model, for these tasks.</abstract>
<identifier type="citekey">long-etal-2023-multimodal</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.217</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.217</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3515</start>
<end>3533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark
%A Long, Yuxing
%A Hui, Binyuan
%A Yuan, Caixia
%A Huang, Fei
%A Li, Yongbin
%A Wang, Xiaojie
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F long-etal-2023-multimodal
%X Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario. This paper introduces a new dataset SURE (Multimodal Recommendation Dialog with Subjective Preference), which contains 12K shopping dialogs in complex store scenes. The data is built in two phases with human annotations to ensure quality and diversity. SURE is well-annotated with subjective preferences and recommendation acts proposed by sales experts. A comprehensive analysis is given to reveal the distinguishing features of SURE. Three benchmark tasks are then proposed on the data to evaluate the capability of multimodal recommendation agents. Basing on the SURE, we propose a baseline model, powered by a state-of-the-art multimodal model, for these tasks.
%R 10.18653/v1/2023.findings-acl.217
%U https://aclanthology.org/2023.findings-acl.217
%U https://doi.org/10.18653/v1/2023.findings-acl.217
%P 3515-3533
Markdown (Informal)
[Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark](https://aclanthology.org/2023.findings-acl.217) (Long et al., Findings 2023)
ACL