Incorporating Syntactic Constraints in Recognizing Handwritten Sentences
Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Natural Language. Pages 1262-1266.
Abstract
The output of handwritten word recognizers (HWR) tends to be very noisy due to various factors . In order to compensate for this behaviour, several choices of the HWR must be initially considered. In the case of handwritten sentence/phrase recognition, linguistic co nstraints may be applied in order to improve the results of the HWR. This paper discusses two statistical methods of applying syntactic constraints to the output of an HWR on input consisting of sentences/phrases. Both methods are based on syntactic categories (tags) associated with words. The first is a purely statistical method, the second is a hybrid m et hod which combines higher-level syntactic information (hypertags) with statistical information regarding transitions between hypertags.
@inproceedings{ijcai1993p174,
title = {Incorporating Syntactic Constraints in Recognizing Handwritten Sentences},
author = {Srihari, Rohini K. and Baltus, Charlotte M.},
booktitle = {Proceedings of the Thirteenth International Joint Conference on
Artificial Intelligence, {IJCAI-93}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ruzena Bajcsy},
pages = {1262--1266},
year = {1993},
note = {Natural Language},
url = {https://ijcai.org/proceedings/1993/174},
}
TY - CPAPER TI - Incorporating Syntactic Constraints in Recognizing Handwritten Sentences AU - Srihari, Rohini K. AU - Baltus, Charlotte M. T2 - Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93 PB - International Joint Conferences on Artificial Intelligence PY - 1993 SP - 1262 EP - 1266 UR - https://ijcai.org/proceedings/1993/174 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
