Publications

@inproceedings{yamazaki_open-domain_2023,

title = {An Open-Domain Avatar Chatbot by Exploiting a Large Language Model},

author = {T. Yamazaki and T. Mizumoto and K. Yoshikawa and M. Ohagi and T. Kawamoto and T. Sato},

editor = {S. Stoyanchev and S. Joty and D. Schlangen and O. Dusek and C. Kennington and M. Alikhani},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105017641158&partnerID=40&md5=5a401bfaeb301f99b444debdd792272c},

isbn = {9798891760288 (ISBN)},

year  = {2023},

date = {2023-01-01},

pages = {428–432},

publisher = {Association for Computational Linguistics (ACL)},

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. © 2025 Elsevier B.V., All rights reserved.},

keywords = {Chatbots, Computational Linguistics, Dialogue systems, Human levels, Interactive computer graphics, Language Model, Multimodal dialogue systems, Multimodal integration, Natural language processing systems, Research communities, Speech processing, Virtual Reality, Virtual-reality environment},

pubstate = {published},

tppubtype = {inproceedings}

}