Show simple item record

dc.contributor.authorPineau, Joelle
dc.date.accessioned2018-03-08T21:37:28Z
dc.date.available2018-03-08T21:37:28Z
dc.date.issued2018-02-22
dc.identifier.urihttp://hdl.handle.net/1853/59408
dc.descriptionPresented on February 22, 2018 in the Klaus Advanced Computing Building, Atrium, Georgia Tech.en_US
dc.descriptionJoelle Pineau, Associate Professor of Computer Science at McGill University and Co-director of the Reasoning and Learning Lab.en_US
dc.descriptionML@GT Spring Lecture Event.en_US
dc.descriptionRuntime: 70:57 minutesen_US
dc.description.abstractThe 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.en_US
dc.format.extent70:57 minutes
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.relation.ispartofseriesMachine Learning@Georgia Tech Seminars (ML@GT)en_US
dc.subjectDailogue systemsen_US
dc.subjectDatasetsen_US
dc.subjectMachine learningen_US
dc.titleData-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challengesen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameMcGill Universityen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record