@inproceedings{lee-etal-2024-stark,
title = "Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge",
author = "Lee, Young-Jun and
Lee, Dokyong and
Youn, Junyoung and
Oh, Kyeong-Jin and
Ko, Byungsoo and
Hyeon, Jonghwan and
Choi, Ho-Jin",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.708",
pages = "12137--12162",
abstract = "Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce , a large-scale long-term multi-modal dialogue dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct automatically, we propose a novel multi-modal contextualization framework, , that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed image aligner. Using our , we train a multi-modal conversation model, 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. The code, dataset, and model will be publicly released after publication.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-stark">
<titleInfo>
<title>Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-Jun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dokyong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyoung</namePart>
<namePart type="family">Youn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyeong-Jin</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byungsoo</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonghwan</namePart>
<namePart type="family">Hyeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ho-Jin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce , a large-scale long-term multi-modal dialogue dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct automatically, we propose a novel multi-modal contextualization framework, , that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed image aligner. Using our , we train a multi-modal conversation model, 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. The code, dataset, and model will be publicly released after publication.</abstract>
<identifier type="citekey">lee-etal-2024-stark</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.708</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12137</start>
<end>12162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge
%A Lee, Young-Jun
%A Lee, Dokyong
%A Youn, Junyoung
%A Oh, Kyeong-Jin
%A Ko, Byungsoo
%A Hyeon, Jonghwan
%A Choi, Ho-Jin
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F lee-etal-2024-stark
%X Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce , a large-scale long-term multi-modal dialogue dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct automatically, we propose a novel multi-modal contextualization framework, , that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed image aligner. Using our , we train a multi-modal conversation model, 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. The code, dataset, and model will be publicly released after publication.
%U https://aclanthology.org/2024.findings-emnlp.708
%P 12137-12162
Markdown (Informal)
[Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge](https://aclanthology.org/2024.findings-emnlp.708) (Lee et al., Findings 2024)
ACL
- Young-Jun Lee, Dokyong Lee, Junyoung Youn, Kyeong-Jin Oh, Byungsoo Ko, Jonghwan Hyeon, and Ho-Jin Choi. 2024. Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12137–12162, Miami, Florida, USA. Association for Computational Linguistics.