NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Corpus-Based Optimization of Language Models Derived from Unification GrammarsWe describe a technique which makes it feasible to improve the performance of a language model derived from a manually constructed unification grammar, using low-quality untranscribed speech data and a minimum of human annotation. The method is on a medium-vocabulary spoken language command and control task.
Document ID
20040051248
Acquisition Source
Headquarters
Document Type
Other
Authors
Rayner, Manny
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Hockey, Beth Ann
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
James, Frankie
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Bratt, Harry
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Bratt, Elizabeth O.
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Gawron, Mark
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Goldwater, Sharon
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Dowding, John
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Bhagat, Amrita
(Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Date Acquired
August 21, 2013
Publication Date
April 10, 2000
Subject Category
Computer Programming And Software
Report/Patent Number
RIACS-TR-00.08
ACL-397
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
Document Inquiry

Available Downloads

There are no available downloads for this record.
No Preview Available