Friday, October 28, 2016 - 10:30am

Location:

Speaker:

Event Website:

From Naming Concrete Objects to Sharing Abstract Thought:  Vision-to-Language Begins to Grow Up

ABSTRACT  Beginning with the philosophical and cognitive underpinnings of referring expression generation, and ending with theoretical, algorithmic and applied contributions in mainstream vision-to-language research, I will discuss some of my work through the years towards the ultimate goal of helping humans and computers to communicate.  This will be a multi-modal, multi-disciplinary talk (with pictures!), aimed to be interesting no matter what your background is. 

BIO  Margaret Mitchell is a Senior Research Scientist in Google's Machine Intelligence Research in Seattle, WA.  She works on advancing artificial intelligence in a way that is interpretable, understanding of art and literature, and respectful of user privacy.

She was a founding researcher in Microsoft's Cognition Group, focusing on advancing artificial intelligence towards positive goals.  Before MSR, she was a postdoctoral researcher at The Johns Hopkins University Center of Excellence, where she mainly focused on semantic role labeling and sentiment analysis using graphical models, working under Benjamin Van Durme.  Before that, she was a postgraduate (Ph.D.) student in the natural language generation (NLG) group at the University of Aberdeen, where she focused on how to naturally refer to visible, everyday objects.  She primarily worked with Kees van Deemter and Ehud Reiter. 

She spent a good chunk of 2008 getting a Master's in Computational Linguistics at the University of Washington, studying under Emily Bender and Fei Xia. 

Simultaneously (2005 - 2012), she worked on and off at the Center for Spoken Language Understanding, part of OHSU, in Portland, Oregon.  Her title changed with time (research assistant/associate/visiting scholar), but throughout, she worked on technology that leverages syntactic and phonetic characteristics to aid those with neurological disorders.  Brian Roark was her boss/mentor/supervisor. 

She continue to balance her time between language generation, applications for clinical domains, and core AI research.

FACULTY HOST  Florian Metze

Keywords: