Assessment Of Smoothing Methods And Complex Stochastic Language Modeling

Assessment Of Smoothing Methods And Complex Stochastic Language Modeling

Cached

Download Links

[www.informatik.rwth-aachen.de]

by Sven Martin , Christoph Hamacher , Jörg Liermann , Frank Wessel , Hermann Ney

Venue:	IN PROCEEDINGS OF THE 6TH EUROPEAN CONFERENCE ON SPEECH COMMUNICATION AND TECHNOLOGY
Citations:	10 - 2 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Assessment of smoothing methods and complex stochastic language modeling	INFERENCE
AUTHOR NAME	Sven Martin	user correction - Legacy Corrections
AUTHOR AFFIL	1	user correction - Legacy Corrections
AUTHOR NAME	Christoph Hamacher	user correction - Legacy Corrections
AUTHOR AFFIL	Lehrstuhl fur Informatik VI, RWTH Aachen-- University of Technology	user correction - Legacy Corrections
AUTHOR ADDR	Ahornstrae 55, 52056 Aachen, Germany	user correction - Legacy Corrections
AUTHOR NAME	Jörg Liermann	user correction - Legacy Corrections
AUTHOR NAME	J Org Liermann	user correction - Legacy Corrections
AUTHOR AFFIL	Lehrstuhl fur Informatik VI, RWTH Aachen-- University of Technology	user correction - Legacy Corrections
AUTHOR ADDR	Ahornstrae 55, 52056 Aachen, Germany	user correction - Legacy Corrections
AUTHOR NAME	Frank Wessel	user correction - Legacy Corrections
AUTHOR AFFIL	Lehrstuhl fur Informatik VI, RWTH Aachen-- University of Technology	user correction - Legacy Corrections
AUTHOR ADDR	Ahornstrae 55, 52056 Aachen, Germany	user correction - Legacy Corrections
AUTHOR NAME	Hermann Ney	user correction - Legacy Corrections
AUTHOR AFFIL	Lehrstuhl fur Informatik VI, RWTH Aachen-- University of Technology	user correction - Legacy Corrections
AUTHOR ADDR	Ahornstrae 55, 52056 Aachen, Germany	user correction - Legacy Corrections
ABSTRACT	This paper studies the overall effect of language modeling on perplexity and word error rate, starting from a trigram model with a standard smoothing method up to complex state--of--the-- art language models: (1) We compare different smoothing methods, namely linear vs. absolute discounting, interpolation vs. backing-off, and back-off functions based on relative frequencies vs. singleton events. (2) We show the effect of complex language model techniques by using distant-trigrams and automatically selected word classes and word phrases using a maximum likelihood criterion (i.e. minimum perplexity). (3) We show the overall gain of the combined application of the above techniques, as opposed to their separate assessment in past publications. (4) We give perplexity and word error rate results on the North American Business corpus (NAB) with a training text of about 240 million words and on the German Verbmobil corpus. 1. INTRODUCTION: LANGUAGE MODELING In this paper, a statistical speec...	user correction - Legacy Corrections
YEAR	1999	INFERENCE
VENUE	In Proceedings of the 6th European Conference on Speech Communication and Technology	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	1939--1942	INFERENCE
VOLUME	5	INFERENCE
CITATIONS	3 found	ParsCit 1.0