Miutsu: NTU's TaskBot for the Alexa Prize

TL;DR

Miutsu is a multi-domain conversational AI designed for the Alexa Prize, capable of assisting users with complex, multi-step tasks in home improvement and cooking through an integrated dialogue system.

Contribution

This paper presents the design and architecture of Miutsu, a novel TaskBot that handles multi-step tasks and integrates various conversational modules for engaging interactions.

Findings

Successfully assisted users in complex tasks in two domains

Developed a dialogue flow for robust multi-step task handling

Faced and addressed challenges in multi-domain conversational AI

Abstract

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 conversational 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.