THIS IS AN ONLINE LECTURE
https://columbiauniversity.zoom.us/j/296632237
Meeting ID: 296 632 237
Learning Language through Interaction
Computer Science Distinguished Lecture
Hal Daume (University of Maryland)
ABSTRACT:
To have the broadest possible positive impact, machine learning-based natural language processing systems must be able to (a) learn when limited training data exists for the target tasks, languages (and varieties), and domains of interest, and (b) identify and mitigate potential harms in their use, in particular arising from the signals on which they are trained. I will first present new algorithms and applications for learning language processing systems through interaction with people, where implicit and/or explicit user feedback drives learning. I will then discuss learning challenges around "fairness" and how such interactive learning mechanisms can help address them.
BIOGRAPHY:
To have the broadest possible positive impact, machine learning-based natural language processing systems must be able to (a) learn when limited training data exists for the target tasks, languages (and varieties), and domains of interest, and (b) identify and mitigate potential harms in their use, in particular arising from the signals on which they are trained. I will first present new algorithms and applications for learning language processing systems through interaction with people, where implicit and/or explicit user feedback drives learning. I will then discuss learning challenges around "fairness" and how such interactive learning mechanisms can help address them.
