Corpora: Discovering new senses

Dimitris K. (svedk@svenska.gu.se)
Tue, 23 Nov 1999 10:59:56 +0100

Dear List members,
I am interested in work related to discovering/identifying NEW
senses in corpora, possibly with the help of existing monolingual MRDs
such as LDOCE (or even large ontologies).
I am aware of some points of departure, such as the work done
by Prof. Y. Wilks described in various papers, Bob Krovetz and S.
Surcin.
Note that I am *not* interested on classifying NEW words in the sense
of, for instance Dekang Lin's work in :
"Automatic Retrieval and Clustering of Similar Words" rather, how
one can observe/discover new senses of already -lexicalized- words,
as automatically as possible.

Sense tagging might have been a bottleneck for such work in the past
but since there is much work going on, around sense disambiguation,
are there any recent attempts to use sense tagging (or other
methodologies)
for the discovery of new senses?

Any pointers, references are welcome.
Send personal email to: svedk@svenska.gu.se

Best,
Dimitrios Kokkinakis