@inproceedings{yamazaki-etal-2023-open,
title = "An Open-Domain Avatar Chatbot by Exploiting a Large Language Model",
author = "Yamazaki, Takato and
Mizumoto, Tomoya and
Yoshikawa, Katsumasa and
Ohagi, Masaya and
Kawamoto, Toshiki and
Sato, Toshinori",
editor = "Stoyanchev, Svetlana and
Joty, Shafiq and
Schlangen, David and
Dusek, Ondrej and
Kennington, Casey and
Alikhani, Malihe",
booktitle = "Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigdial-1.40/",
doi = "10.18653/v1/2023.sigdial-1.40",
pages = "428--432",
abstract = "With the ambition to create avatars capable of human-level casual conversation, we developed an open-domain avatar chatbot, situated in a virtual reality environment, that employs a large language model (LLM). Introducing the LLM posed several challenges for multimodal integration, such as developing techniques to align diverse outputs and avatar control, as well as addressing the issue of slow generation speed. To address these challenges, we integrated various external modules into our system. Our system is based on the award-winning model from the Dialogue System Live Competition 5. Through this work, we hope to stimulate discussions within the research community about the potential and challenges of multimodal dialogue systems enhanced with LLMs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamazaki-etal-2023-open">
<titleInfo>
<title>An Open-Domain Avatar Chatbot by Exploiting a Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takato</namePart>
<namePart type="family">Yamazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Mizumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsumasa</namePart>
<namePart type="family">Yoshikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaya</namePart>
<namePart type="family">Ohagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiki</namePart>
<namePart type="family">Kawamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshinori</namePart>
<namePart type="family">Sato</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 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the ambition to create avatars capable of human-level casual conversation, we developed an open-domain avatar chatbot, situated in a virtual reality environment, that employs a large language model (LLM). Introducing the LLM posed several challenges for multimodal integration, such as developing techniques to align diverse outputs and avatar control, as well as addressing the issue of slow generation speed. To address these challenges, we integrated various external modules into our system. Our system is based on the award-winning model from the Dialogue System Live Competition 5. Through this work, we hope to stimulate discussions within the research community about the potential and challenges of multimodal dialogue systems enhanced with LLMs.</abstract>
<identifier type="citekey">yamazaki-etal-2023-open</identifier>
<identifier type="doi">10.18653/v1/2023.sigdial-1.40</identifier>
<location>
<url>https://aclanthology.org/2023.sigdial-1.40/</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>428</start>
<end>432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Open-Domain Avatar Chatbot by Exploiting a Large Language Model
%A Yamazaki, Takato
%A Mizumoto, Tomoya
%A Yoshikawa, Katsumasa
%A Ohagi, Masaya
%A Kawamoto, Toshiki
%A Sato, Toshinori
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F yamazaki-etal-2023-open
%X With the ambition to create avatars capable of human-level casual conversation, we developed an open-domain avatar chatbot, situated in a virtual reality environment, that employs a large language model (LLM). Introducing the LLM posed several challenges for multimodal integration, such as developing techniques to align diverse outputs and avatar control, as well as addressing the issue of slow generation speed. To address these challenges, we integrated various external modules into our system. Our system is based on the award-winning model from the Dialogue System Live Competition 5. Through this work, we hope to stimulate discussions within the research community about the potential and challenges of multimodal dialogue systems enhanced with LLMs.
%R 10.18653/v1/2023.sigdial-1.40
%U https://aclanthology.org/2023.sigdial-1.40/
%U https://doi.org/10.18653/v1/2023.sigdial-1.40
%P 428-432
Markdown (Informal)
[An Open-Domain Avatar Chatbot by Exploiting a Large Language Model](https://aclanthology.org/2023.sigdial-1.40/) (Yamazaki et al., SIGDIAL 2023)
ACL
- Takato Yamazaki, Tomoya Mizumoto, Katsumasa Yoshikawa, Masaya Ohagi, Toshiki Kawamoto, and Toshinori Sato. 2023. An Open-Domain Avatar Chatbot by Exploiting a Large Language Model. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 428–432, Prague, Czechia. Association for Computational Linguistics.