Alexa Prize TaskBot Challenge 1

The challenge is focused on developing agents that assist customers in completing tasks requiring multiple steps and decisions. It's the first conversational AI challenge to incorporate multimodal (voice and vision) customer experiences.

We (Twiz Team) designed a multimodal conversational bot for the Alexa Prize TaskBot Challenge. Our design envisions the support of an engaging experience, where users are guided through multimodal conversations, towards the successful completion of the selected task. This is achieved through four key principles: a) robust dialog interaction, by making core dialog components (utterance processing, dialog manager, and response generator) tailored for an in-the-wild setting, b) effective and conversational task grounding, c) delivery of an immersive multimodal task guiding experience, and d) engagement maximization and user cognitive stimuli. In the following sections, we present the proposed methods to tackle each one of these principles, leading to a novel multimodal curiosity-exploration task guiding conversational assistant, that manages to balance user engagement and cognitive load, while guiding users through complex tasks.

Twiz Team & Twiz Bot

Check our published paper (Lisbon, 2022).

References

2022

  1. TWIZ: A conversational Task Wizard with multimodal curiosity-exploration
    NOVA University Lisbon
    In Alexa Prize TaskBot Challenge 1 Proceedings , 2022