Do you have published material on this? The same idea occurs as a
tentative conclusion in Elworthy's paper. I think more detail and
numbers would be of general interest.
how about this one?
Paper: cmp-lg/9410027
From: Andre.Kempe@xerox.fr (Andre Kempe)
Date: Tue, 25 Oct 1994 19:49:27 --100
Title: Probabilistic Tagging with Feature Structures
Author: Andre Kempe (University of Stuttgart)
Comments: Coling-94, 85 KB, 5 pages, uuencoded compressed postscript
Report-no: cmp-lg/yymmnnn
The described tagger is based on a hidden Markov model and uses tags
composed of features such as part-of-speech, gender, etc. The
contextual probability of a tag (state transition probability) is
deduced from the contextual probabilities of its
feature-value-pairs. This approach is advantageous when the
available training corpus is small and the tag set large, which can
be the case with morphologically rich languages.