BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Seminar
DESCRIPTION:Learning Machines Seminar Series\n\n"Natural Language Understan
 ding with Incidental Supervision"\n\nThe fundamental issue underlying natur
 al language understanding is that of semantics – there is a need to move to
 ward understanding natural language at an appropriate level of abstraction\
 , beyond the word level\, in order to support knowledge extraction\, natura
 l language understanding\, and communication. Machine Learning and Inferenc
 e methods have become ubiquitous in our attempt to induce semantic represen
 tations of natural language and support decisions that depend on it. Howeve
 r\, learning models for these tasks are difficult\, partly since generating
  supervision signals for it is costly and does not scale. Consequently\, ma
 king natural language understanding decisions\, which typically depend on m
 ultiple\, interdependent\, models\, becomes even more challenging.\n\nI wil
 l describe some of our research on developing machine learning and inferenc
 e methods in pursuit of understanding natural language text. I will point t
 o some of the key challenges and some possible directions for studying this
  problem from a principled perspective and focus on identifying and using i
 ncidental supervision signals.\n\nBIO:\n\nDan Roth is the Eduardo D. Glandt
  Distinguished Professor at the Department of Computer and Information Scie
 nce\, University of Pennsylvania\, and a Fellow of the AAAS\, the ACM\, AAA
 I\, and the ACL.\n\nIn 2017 Roth was awarded the John McCarthy Award\, the 
 highest award the AI community gives to mid-career AI researchers. Roth was
  recognized “for major conceptual and theoretical advances in the modeling 
 of natural language understanding\, machine learning\, and reasoning.”\n\nR
 oth has published broadly in machine learning\, natural language processing
 \, knowledge representation and reasoning\, and learning theory\, and has d
 eveloped advanced machine learning based tools for natural language applica
 tions that are being used widely. Until February 2017 Roth was the Editor-i
 n-Chief of the Journal of Artificial Intelligence Research (JAIR).\n\nProf.
  Roth received his B.A Summa cum laude in Mathematics from the Technion\, I
 srael\, and his Ph.D. in Computer Science from Harvard University in 1995.
DTEND:20180921T173000Z
DTSTAMP:20260306T182013Z
DTSTART:20180921T160000Z
GEO:40.755644;-73.956097
LOCATION:Bloomberg Center\, 161
SEQUENCE:0
SUMMARY:LMSS @ Cornell Tech: Dan Roth (University of Pennsylvania)
UID:tag:localist.com\,2008:EventInstance_3572803
URL:https://events.cornell.edu/event/lmss_cornell_tech_dan_roth_upenn
END:VEVENT
END:VCALENDAR