[Talks] Sharon Caraballo Thesis Defense in Lubrano on July 28, 2000 at 11 AM

[talks-admin@list.cs.brown.edu]

			  CS Thesis Defense
		  The Department of Computer Science
			   BROWN UNIVERSITY

			       presents

			   Sharon Caraballo

		  Friday, July 28, 2000 at 11:00 AM

	       Lubrano Conference Room (CIT 4th floor)

	          
``Automatic Construction of Hypernym-Labeled Noun Hierarchy from Text''

			       
			       Abstract

Many language processing tasks are dependent on large databases of
lexical semantic information, such as WordNet.  These hand-built
resources are tremendously time-consuming to create and may be lacking
in coverage.  They may be particularly inappropriate for text from a
single domain, both because domain-specific terms are missing and
because the lexicon contains many words or meanings which would be
extremely rare in that domain.

This thesis describes statistical techniques to automatically extract
semantic information about words from text; specifically, given a
large corpus of text and no additional sources of semantic
information, we build a hierarchy of nouns appearing in the text.  The
hierarchy is in the form of an IS-A tree, where the nodes of the tree
contain one or more nouns, and the ancestors of a node contain
hypernyms of the nouns in that node.  (An English word A is said to be
a hypernym of a word B if native speakers of English accept the
sentence "B is a (kind of) A.")  The techniques presented here could
be used in the construction of updated or domain-specific semantic
resources as needed.  The methods described here provide a substantial
improvement over previously published results; while we could
previously produce a hierarchy whose internal nodes were judged to be
correct hypernyms for 33% of the nouns beneath them, we can now
achieve 56% on this measure.


  
		   Host: Professor Eugene Charniak













************************************************
Eugenia deGouveia
Brown University
Computer Science Department
401-863-7600
egd@cs.brown.edu
************************************************