Loading...
Loading...

Go to the content (press return)

Language modeling using X-grams

Author
Bonafonte, A.; Mariño, J.B.
Type of activity
Presentation of work at congresses
Name of edition
4th International Conference on Spoken Language Processing
Date of publication
1996
Presentation's date
1996-10
Book of congress proceedings
ICSLP 1996: 4th International Conference on Spoken Language Processing: Philadelphia, PA, USA: October 3-6, 1996
First page
394
Last page
397
Publisher
H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE
DOI
https://doi.org/10.1109/ICSLP.1996.607137 Open in new window
Repository
http://hdl.handle.net/2117/102621 Open in new window
URL
http://ieeexplore.ieee.org/document/607137/ Open in new window
Abstract
In this paper, an extension of n-grams, called x-grams, is proposed. In this extension, the memory of the model (n) is not fixed a priori. Instead, large memories are accepted first, and merging criteria are then applied to reduce the complexity and to ensure reliable estimations. The results show how the perplexity obtained with x-grams is smaller than that of n-grams. Furthermore, the complexity is smaller than trigrams and can become close to bigrams.
Citation
Bonafonte, A., Mariño, J. Language modeling using X-grams. A: International Conference on Spoken Language. "Fourth international conference on spoken language, 1996, ICSLP 96: proceedings". Philadelphia, PA: H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996, p. 394-397.
Keywords
Computational complexity0, Computational linguistics, Grammars, Linguistics, Merging, Modelling, Natural languages, Nomograms, Probability
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants

Attachments