Publication:
Adaptive models of English text

Abstract

High quality models of English text with performance approaching that of humans is important for many applications including spelling correction, speech recognition, OCR, and encryption. A number of different statistical models of English are compared with each other and with previous estimates from human subjects. It is concluded that the best current models are word based with part of speech tags. Given sufficient training text, they are able to attain performance comparable to humans.

Citation

Teahan, W.J. & Cleary, J.G. (1997). Adaptive models of English text. (Working paper 97/30). Hamilton, New Zealand: University of Waikato, Department of Computer Science.

Publisher

Department of Computer Science, The University of Waikato

Degree

Type of thesis

Supervisor

Link to supplementary material

Research Projects

Organizational Units

Journal Issue