Design of a linguistic postprocessor using variable memory length Markov models

Authors:
I. Guyon;F. Pereira
Affiliations:
-;-
Venue:
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Year:
1995

Citing 0
Cited 12

On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Predicting the Future of Discrete Sequences from Fractal Representations of the Past

Machine Learning
Recurrent neural networks with small weights implement definite memory machines

Neural Computation
Lexical Post-Processing Optimization for Handwritten Word Recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Rapid on-line temporal sequence prediction by an adaptive agent

Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
OCR post-processing for low density languages

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
A real-time hand tracker using variable-length Markov models of behaviour

Computer Vision and Image Understanding
Real-time 3-D human body tracking using learnt models of behaviour

Computer Vision and Image Understanding
Non-stationary policy learning in 2-player zero sum games

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Learning atomic human actions using variable-length Markov models

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction

Spatial cognition III
Visual speech synthesis by modelling coarticulation dynamics using a non-parametric switching state-space model

International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a linguistic postprocessor for character recognizers. The central module of our system is a trainable variable memory length Markov model (VLMM) that predicts the next character given a variable length window of past characters. The overall system is composed of several finite state automata, including the main VLMM and a proper noun VLMM. The best model reported in the literature (Brown et al., 1992) achieves 1.75 bits per character on the Brown corpus. On that same corpus, our model, trained on 10 times less data, reaches 2.19 bits per character and is 200 times smaller (/spl sime/160,000 parameters). The model was designed for handwriting recognition applications but could also be used for other OCR problems and speech recognition.