UTCS Colloquium/AI: Renata Vieira UNISINOS Sao Leopoldo Brazil Have I mentioned it? ACES 2.402 Friday March 30 2007 at 2:00 p.m.

Contact Name: 
Jenna Whitney
Date: 
Mar 30, 2007 2:00pm - 3:00pm

There is a signup schedule for this event.

Type of Talk:
UTCS Colloquium/AI

Speaker Name/Affiliation: Renata Vieira/UNISIN

OS Sao Leopoldo Brazil

Date/Time: Friday March 30 2007 2:00

p.m. - 3:00 p.m.

Location: ACES 2.402

Host: Raymond Mooney<

br>
Talk Title: Have I mentioned it?

Talk Abstract:
Corefer

ence resolution is a well known NLP task relevant for the more general tas

k of information extraction among others. A related problem is the problem
of identifying if a referring expression is introducing a new entity in th

e text or if it follows previously mentioned ones. Definite descriptions ar

e a type of referring expressions which are highly ambiguous between these

two roles. In fact they sometimes lie in between these two when mentioning
a new entity whose interpretation is anchored in given ones. When developi

ng a classifier that distinguishes between these many roles of definite des

criptions we face not only the old AI problem of grasping common sense and

world knowledge but also the problem of unbalanced data. In this talk I wil

l present some experiments dealing with these problems and I will mention s

ome NLP tasks that the classifier is useful for.

Speaker Bio:
Re

nata Vieira is Professor in the Computer Science Department at Universidade
do Vale do Rio dos Sinos Sao Leopoldo Brazil. She received her PhD from

the University of Edinburgh in 1998. Her research interests
cover issue

s in computational linguistics artificial intelligence including natural

language understanding discourse processing agent communication

knowledge representation ontologies and the semantic web.