Improved language modeling by unsupervised acquisition of structure (1995)
| Venue: | IN PROCEEDINGS OF THE 1995 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING |
| Citations: | 8 - 4 self |
BibTeX
@INPROCEEDINGS{Ries95improvedlanguage,
author = {Klaus Ries and Finn Dag Buø and Ye-Yi Wang},
title = {Improved language modeling by unsupervised acquisition of structure},
booktitle = {IN PROCEEDINGS OF THE 1995 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING},
year = {1995},
publisher = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
The word accuracy of the decoder is improved from 59:1% to 61.1 % by a new method for the unsupervised acquisition of a structural text model. Well recognized sentences even show an improvement from 84.8 % to 91.1%. This method is based on new algorithms for the classification of words and phrases by their context and on new sequence finding procedures. These procedures are designed to work fast and accurately on small and large corpora. They are iterated to build a structural model of a corpus. Further applications in language processing, which exploit the structure nding capabilities of this model, such as preprocessing for neural networks and (hidden) markov models, are proposed.
Citations
| 12 | Class based n-gram models of natural language - Brown, Pietra, et al. - 1992 |
| 1 | Distituent parsing and grammar induction. volume D-91-09 - Magerman, Marcus - 1993 |
| 1 | Ris89] [SL77 - thesis, Karlsruhe - 1994 |
