Interactive Task Learning from GUI-Grounded Natural Language Instructions and Demonstrations

Toby Jia-Jun Li, Tom Mitchell, Brad Myers


Abstract
We show SUGILITE, an intelligent task automation agent that can learn new tasks and relevant associated concepts interactively from the user’s natural language instructions and demonstrations, using the graphical user interfaces (GUIs) of third-party mobile apps. This system provides several interesting features: (1) it allows users to teach new task procedures and concepts through verbal instructions together with demonstration of the steps of a script using GUIs; (2) it supports users in clarifying their intents for demonstrated actions using GUI-grounded verbal instructions; (3) it infers parameters of tasks and their possible values in utterances using the hierarchical structures of the underlying app GUIs; and (4) it generalizes taught concepts to different contexts and task domains. We describe the architecture of the SUGILITE system, explain the design and implementation of its key features, and show a prototype in the form of a conversational assistant on Android.
Anthology ID:
2020.acl-demos.25
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
215–223
URL:
https://www.aclweb.org/anthology/2020.acl-demos.25
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/2020.acl-demos.25.pdf

You can write comments here (and agree to place them under CC-by). They are not guaranteed to stay and there is no e-mail functionality.