We are collecting reference questions for assessment of new metadata
extraction techniques (described below). I would greatly appreciate it if
colleagues send me some sample questions received at the reference desk by
patrons in search of images. Do not send to ARLIS-L but directly to me at
[log in to unmask]
Columbia University has received a grant from the Andrew W. Mellon
Foundation to enhance access to digital images by exploring the use of
existing computational linguistic techniques as a source of metadata.
One of the most serious bottlenecks in digitizing collections is in making
them easy to search. The CLiMB (Computational Linguistics for Metadata
Building) project will bring together the most recent developments in
natural language processing and apply them to the problems of automatically
extracting metadata from text.
Building on earlier results at Columbia in the development of natural
language processing tools that permit large-scale robust analysis of text
data, the CLiMB project includes an extensive component for assessment and
evaluation.
__________________________________________________________________
Mail submissions to [log in to unmask]
For information about joining ARLIS/NA see:
http://www.arlisna.org//membership.html
Send administrative matters (file requests, subscription requests, etc)
to [log in to unmask]
ARLIS-L Archives and subscription maintenance:
http://lsv.uky.edu/archives/arlis-l.html
Questions may be addressed to list owner (Kerri Scannell) at: [log in to unmask]
