Data-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challenges

Author(s)
Pineau, Joelle
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Organizational Unit
Series
Series
Collections
Supplementary to:
Abstract
The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. In this talk I will review several recent models and algorithms based on both discriminative and generative models, and discuss new results on the proper performance measures for such systems. Finally, I will highlight potential ethical issues that arise in dialogue systems research, including: implicit biases, adversarial examples, privacy violations, and safety concerns.
Sponsor
Date
2018-02-22
Extent
70:57 minutes
Resource Type
Moving Image
Text
Resource Subtype
Lecture
Flyer
Rights Statement
Rights URI