Computer Science – Computation and Language
Scientific paper
2000-01-24
Computer Science
Computation and Language
Advisor: Frederick Jelinek, Ph.D. Thesis, 122 pages; removed unused .eps file
Scientific paper
The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an original probabilistic parameterization of a shift-reduce parser. A maximum likelihood reestimation procedure belonging to the class of expectation-maximization algorithms is employed for training the model. Experiments on the Wall Street Journal, Switchboard and Broadcast News corpora show improvement in both perplexity and word error rate - word lattice rescoring - over the standard 3-gram language model. The significance of the thesis lies in presenting an original approach to language modeling that uses the hierarchical - syntactic - structure in natural language to improve on current 3-gram modeling techniques for large vocabulary speech recognition.
No associations
LandOfFree
Exploiting Syntactic Structure for Natural Language Modeling does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Exploiting Syntactic Structure for Natural Language Modeling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Exploiting Syntactic Structure for Natural Language Modeling will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-308843