A Bandit Approach to Posterior Dialog Orchestration Under a Budget

06/22/2019
by   Sohini Upadhyay, et al.
0

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 simulated non-conversational and proprietary conversational datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2019

Towards Personalized Dialog Policies for Conversational Skill Discovery

Many businesses and consumers are extending the capabilities of voice-ba...
research
10/15/2020

Double-Linear Thompson Sampling for Context-Attentive Bandits

In this paper, we analyze and extend an online learning framework known ...
research
02/12/2018

A Unified Implicit Dialog Framework for Conversational Search

We propose a unified Implicit Dialog framework for goal-oriented, inform...
research
04/17/2020

Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills

Being engaging, knowledgeable, and empathetic are all desirable general ...
research
11/22/2017

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models

Dialog response selection is an important step towards natural response ...
research
10/22/2020

Migratable AI: Personalizing Dialog Conversations with migration context

The migration of conversational AI agents across different embodiments i...
research
03/04/2021

Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration

Current state-of-the-art large-scale conversational AI or intelligent di...

Please sign up or login with your details

Forgot password? Click here to reset