There is a signup schedule for this event (UT EID required).

Type

of Talk: UTCS AI

Speaker/Affiliation: Hal Daume/University of Utah

Date/Time: Monday November 10 2008 11:00 a.m.

Location:
TAY 3.128

Host: Ray Mooney

Talk Title: Domain Adaptation i

n Natural Language

Talk Abstract:
Supervised learning technology

has led to systems for part
of speech tagging parsing named entity re

cognition with
accuracies in the high 90%s. Unfortunately the performa

nce
of these systems degrades drastically when they are applied
on

text outside their training domain (typically newswire).
Machine trans

lation systems work fantastically for translating
Parliamentary proceed

ings but fall down when applied to
alternate domains. I''ll discuss re

search that aims to understand
what goes wrong when models are applied

outside their domain
and some (partial) solutions to this problem. I''

ll focus on named
entity recognition and machine translation tasks whe

re we''ll see
a range of different sources of error (some of which are

quite
counter-intuitive!).