Publication: Adaptive models of English text
| dc.contributor.author | Teahan, W.J. | |
| dc.contributor.author | Cleary, John G. | |
| dc.date.accessioned | 2008-10-22T03:04:43Z | |
| dc.date.available | 2008-10-22T03:04:43Z | |
| dc.date.issued | 1997-11 | |
| dc.description.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. | en_US |
| dc.format.mimetype | application/pdf | |
| dc.identifier.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. | en_US |
| dc.identifier.issn | 1170-487X | |
| dc.identifier.uri | https://hdl.handle.net/10289/1126 | |
| dc.language.iso | en | |
| dc.publisher | Department of Computer Science, The University of Waikato | |
| dc.relation.ispartofseries | Computer Science Working Papers | |
| dc.subject | statistical language modeling | en_US |
| dc.subject | the entropy of English | en_US |
| dc.subject | text compression | en_US |
| dc.subject | adaptive n-gram models | en_US |
| dc.subject | PPM text compression scheme | en_US |
| dc.title | Adaptive models of English text | en_US |
| dc.type | Working Paper | en_US |
| dspace.entity.type | Publication | |
| pubs.place-of-publication | Hamilton | en_NZ |
| uow.relation.series | 97/30 |