QUANTIFYING THE CONTRIBUTION OF LANGUAGE MODELING TO WRITER­INDEPENDENT ON­LINE HANDWRITING RECOGNITION

John F. PITRELLI and Eugene H. RATZLAFF

Pen Technologies Group, IBM T. J. Watson Research Center
P. O. Box 218, Yorktown Heights, NY 10598, U.S.A.
E­mail: fpitrelli,ratzlaffg@us.ibm.com

We describe experiments varying the degree of language­model constraint applied to writer­independent on­line handwriting recognition. Six types of models are used, varying statistical components and hard constraints which govern recognition search during the sequencing of characters to form valid texts. Experiments on constrained texts, such as dates and phone numbers, show that although tighter language models cause more inputs to be out­of­domain, they can still eliminate up to 50% of string errors and 75% of character errors compared to using a null language model.

In: L.R.B. Schomaker and L.G. Vuurpijl (Eds.)
Proceedings of the Seventh International Workshop on Frontiers
in Handwriting Recognition, September 11-13 2000, Amsterdam,
Nijmegen: International Unipen Foundation,
ISBN 90-76942-01-3
pp. 383-392.