Miutsu: NTU’s TaskBot for the Alexa Prize
Published in Arxiv, 2022
This paper introduces Miutsu, National Taiwan University’s Alexa Prize TaskBot, which is designed to assist users in completing tasks requiring multiple steps and decisions in two different domains – home improvement and cooking. We overview our system design and architectural goals, and detail the proposed core elements, including question answering, task retrieval, social chatting, and various conver- sational modules. A dialogue flow is proposed to provide a robust and engaging conversation when handling complex tasks. We discuss the faced challenges during the competition and potential future work.
Recommended citation:
@misc{
https://doi.org/10.48550/arxiv.2205.07446,
doi = {10.48550/ARXIV.2205.07446},
url = {https://arxiv.org/abs/2205.07446},
author = {Lin, Yen-Ting and Kuo, Hui-Chi and Xu, Ze-Song and Chiu, Ssu and Hung, Chieh-Chi and Chen, Yi-Cheng and Huang, Chao-Wei and Chen, Yun-Nung},
keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Miutsu: NTU's TaskBot for the Alexa Prize},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution Non Commercial No Derivatives 4.0 International}
}
Leave a Comment