Computer Science – Computation and Language
Scientific paper
1994-11-08
Computer Science
Computation and Language
PostScript, 19 pages, 250kb; from Proceedings of the 9th Annual Conference of the UW Centre for the New OED and Text Research,
Scientific paper
We describe an automated method for identifying classes of morphologically related words in an on-line dictionary, and for linking individual senses in the derived form to one or more senses in the base form by means of morphological relation attributes. We also present an algorithm for computing a score reflecting the system=92s certainty in these derivational links; this computation relies on the content of semantic relations associated with each sense, which are extracted automatically by parsing each sense definition and subjecting the parse structure to automated semantic analysis. By processing the entire set of headwords in the dictionary in this fashion we create a large set of directed derivational graphs, which can then be accessed by other components in our broad-coverage NLP system. Spurious or unlikely derivations are not discarded, but are rather added to the dictionary and assigned a negative score; this allows the system to handle non-standard uses of these forms.
Corporation Microsoft
Pentheroudakis Joseph
Vanderwende Lucy
No associations
LandOfFree
Automatically Identifying Morphological Relations in = Machine-Readable Dictionaries does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Automatically Identifying Morphological Relations in = Machine-Readable Dictionaries, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automatically Identifying Morphological Relations in = Machine-Readable Dictionaries will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-229965