Toward Skills Dialog Orchestration with Online Learning
Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay, Mayank Agarwal, Yasaman Khazaeni, Irina Rish
Abstract
Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orchestrate multiple independently trained dialog agents, or skills, to create a unified system is of particular significance. In this work, we study the task of online posterior dialog orchestration, where we define posterior orchestration as the task of selecting a subset of skills which most appropriately answer a user input using features extracted from both the user input and the individual skills. To account for the various costs associated with extracting skill features, we consider online posterior orchestration under a skill execution budget. We formalize this setting as Context Attentive Bandit with Observations (CABO), a variant of context attentive bandits, and evaluate it on proprietary conversational datasets.
BibTeX
@inproceedings{icassp2021_towardskillsdial,
title = {Toward Skills Dialog Orchestration with Online Learning},
author = {Djallel Bouneffouf and Raphaël Féraud and Sohini Upadhyay and Mayank Agarwal and Yasaman Khazaeni and Irina Rish},
booktitle = {ICASSP 2021},
year = {2021}
}