Data-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challenges
MetadataShow full item record
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.