Rapid language model development for new task domains

Rapid language model development for new task domains (1998)

Cached

Download Links

by Lucian Galescu , Eric Ringger , James Allen

Venue:	Proc. First International Conference on Language Resources and Evaluation (LREC
Citations:	16 - 6 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Rapid language model development for new task domains	INFERENCE
AUTHOR NAME	Lucian Galescu	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627 USA	SVM HeaderParse 0.2
AUTHOR NAME	Eric Ringger	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627 USA	SVM HeaderParse 0.2
AUTHOR NAME	James Allen	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627 USA	SVM HeaderParse 0.2
ABSTRACT	Data sparseness has been regularly indicted as the primary problem in statistical language modelling. We go one step further to consider the situation when no text data is available for the target domain. We present two techniques for building efficient language models quickly for new domains. The first technique is based on using a context-free grammar to generate a corpus of word collocations. The second is an adaptation technique based on using out-of-domain corpora to estimate target domain language models. We report results of successfully using these two techniques individually and in combination to build efficient models for a spontaneous speech recognition task in a medium-sized vocabulary domain. 1.	SVM HeaderParse 0.2
YEAR	1998	INFERENCE
VENUE	Proc. First International Conference on Language Resources and Evaluation (LREC	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	24 found	ParsCit 1.0