NASA NTRS · 20040051248
Corpus-Based Optimization of Language Models Derived from Unification Grammars
Abstract
We 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.
Keep this discovery
Explore connections, maps & timelines
Rayner, Manny, Hockey, Beth Ann, James, Frankie, Bratt, Harry, Bratt, Elizabeth O., Gawron, Mark, Goldwater, Sharon, Dowding, John, Bhagat, Amrita. 2000-04-10. Corpus-Based Optimization of Language Models Derived from Unification Grammars. https://ntrs.nasa.gov/citations/20040051248
Cite the original work for its findings. Save a collection to share your selection of sources.