UTCS Colloquium/AI: Dan Jurafsky/Stanford University Inducing Semantic Taxonomies for Words ACES 2.402 Friday November 16 2007 11:00 a.m.
Type of Talk: UTCS Colloquium/AI
Speaker/Affiliation: Dan Ju
Date/Time: Friday November 16 2007 11
Location: ACES 2.402
Host: Ray Mooney
itle: Inducing Semantic Taxonomies for Words
ne resources for word meaning like dictionaries and
thesauri are a usef
ul resource for natural language processing.
But English has a lot of w
ords and adds more every day.
Hand-built resources can''t keep up. We
report on three studies
on inducing the meaning of words from text on t
he Web in
the context of augmenting WordNet a large online thesaurus <
br>of English. We first describe a semi-supervised method for
when a new word is a %60hypernym'' or in the ''is-a''
relation with ano
ther word based on combining %60weak learner''
hypernym detection patt
erns. We then show a new probabilistic
algorithm for taxonomy induction
which incorporates evidence
from multiple relation detectors (for hypo
nymy and synonymy)
to optimize the entire structure of the taxonomy. Fi
we show how to improve the granularity of word senses in
esaurus by clustering word senses. This talk describes
joint work with
Rion Snow and Andrew Ng.
Dan Jurafsky is an associat
e professor in the Department
of Linguistics and by courtesy in the De
partment of Computer
Science at Stanford University. Before Stanford h
for 8 years at the University of Colorado Boulder. Dan
udies statistical models of human and machine processing
of text and sp
eech focusing lately on computational models
of semantics and discours
e and on conversational speech.
- Awards & Honors
- About Us
- Student Engagement and Support
- Masters Program
- Ph.D. Program
- Financial Information
- Prospective Students
- Incoming Students
- Current Students
- Portfolio Program in Robotics
- Curricular Practical Training
- Grad Student Talks
- UTCS Direct