A Variable-Length Category-Based N-Gram Language Model

A Variable-Length Category-Based N-Gram Language Model (1996)

by T. R. Niesler , P. C. Woodland

Venue:	IN PROCEEDINGS, IEEE ICASSP
Citations:	42 - 6 self

User correction supplied by mph

Datum	Value	Source
TITLE	A Variable-Length Category-Based N-Gram Language Model	user correction - Legacy Corrections
AUTHOR NAME	T. R. Niesler	user correction
AUTHOR AFFIL	Cambridge University Engineering Department,; Trumpington Street, Cambridge, CB2 1PZ	user correction
AUTHOR ADDR	England.	user correction
AUTHOR NAME	P. C. Woodland	user correction
AUTHOR AFFIL	Cambridge University Engineering Department,; Trumpington Street, Cambridge, CB2 1PZ	user correction
AUTHOR ADDR	England.	user correction
ABSTRACT	A language model based on word-category n-grams and ambiguous category membership with n increased selectively to trade compactness for performance is presented. The use of categories leads intrinsically to a compact model with the ability to generalise to unseen word sequences, and diminishes the spareseness of the training data, thereby making larger n feasible. The language model implicitly involves a statistical tagging operation, which may be used explicitly to assign category assigments to untagged text. Experiments on the LOB corpus show the optimal model-building strategy to yield improved results with respect to conventional n-gram methods, and when used as a tagger, the model is seen to perform well in relation to a standard benchmark.	user correction
YEAR	1996	INFERENCE
VENUE	IN PROCEEDINGS, IEEE ICASSP	user correction
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	164--167	INFERENCE
CITATIONS	8 found	ParsCit 1.0