UTCS Colloquia/AI- Ellen Riloff/University of Utah, "Adventures in Bootstrapping: Acquiring Lexical Knowledge for NLP", ACES 2.402"

Contact Name: 
Jenna Whitney
Date: 
Mar 4, 2011 11:00am - 12:00pm

There is a sign-up schedule for this event that can be found at

http://www.cs.utexas.edu/department/webevent/utcs/events/cgi/list_event

s.cgi

Type of Talk: UTCS Colloquia/AI

Speaker/Affiliation: Ellen

Riloff/University of Utah

Talk Audience: UTCS Faculty, Grads, Underg

rads, and Outside interested Parties

Date/Time: Friday, March 4, 20

11, 11:00 a.m.

Location: ACES 2.402

Host: Raymond J. Mooney

nTalk Title: Adventures in Bootstrapping: Acquiring Lexical Knowledge for N

LP

Talk Abstract:
Understanding natural language requires many types
of lexical knowledge. Some lexical resources have been created (e.g., Wor

dNet and FrameNet), but they are far from complete and they are rarely suf

ficient for informal jargon or specialized domains. Starting in 1997, the

Utah NLP lab has been developing bootstrapping techniques to automatically

acquire lexical knowledge from unannotated text collections. We have create

d several bootstrapping algorithms to induce semantic lexicons, as well as
resources for subjectivity classification, event extraction, and plot un

it analysis. Most recently, we used bootstrapping to create a contextual s

emantic tagger, given only seed words and domain-specific texts for traini

ng. In this talk, we will overview the bootstrapping methods that we have

developed and try to distill out general lessons we have learned about what
it takes to make bootstrapping work.

Speaker Bio:
Ellen Riloff is a

n Associate Professor of Computer Science in the School of Computing at the
University of Utah. Her primary research areas are information extraction

, semantic tagging and lexicon induction, coreference resolution, and sub

jectivity analysis. A major emphasis of her research has been automatically
acquiring knowledge needed for natural language processing using bootstrap

ping methods that can learn from unannotated texts with minimal human super

vision. Her professional roles have included service on the NAACL Executive
Board, Human Language Technology (HLT) Advisory Board, DARPA/NSF Questio

n Answering Roadmap Committee, Computational Linguistics Editorial Board,
and as CoNLL Program Co-Chair and Faculty Advisor for the ACL Student Rese

arch Workshop.