3/2/2006
3:30pm-4:30pm
ECCR 265
|
Fine-Grained Differences and Similarities in Meanings in Natural Language Processing
University of Toronto
Writing or speaking requires making choices from words and syntactic
constructions that have similar but not identical meanings. Are two parties
"foes" or "enemies"? Did John meet Mary or was Mary met by John? An important
component of language understanding is recognizing the implications of the
nuances in the speaker's or writer's choices. I will describe our research on
computational aspects of linguistic nuance, focusing on the differentiation of
near-synonyms and on the consequences that arise for knowledge representation
formalisms and machine translation. In addition, I will discuss how
contemporary views of meaning in computational linguistics need to be broadened
to take into account the choices that the speaker or writer makes.
Graeme Hirst is a professor of computer science at the
University of Toronto, whose research covers a broad but integrated range of
topics in computational linguistics, natural language understanding, and
related areas of cognitive science. He is the author of two monographs:
Anaphora in Natural Language Understanding and Semantic Interpretation
and the Resolution of Ambiguity. Hirst has received two awards for
excellence in teaching, and has supervised graduate students in more than 35
theses and dissertations, four of which have been published as books.
|
The Department holds colloquia throughout the Fall and Spring semesters. These
colloquia, open to the public, are typically held on Thursday afternoons, but
sometimes occur at other times as well.
If you would like to receive email notification of upcoming colloquia,
subscribe to our
Colloquia Mailing List.
If you would like to schedule a colloquium, see
Colloquium Scheduling.
Sign language interpreters are available upon request. Please contact
Stephanie Morris at least five days prior to the colloquium.
|
