Building scalable n-gram language models using maximum likelihoo

Details Building scalable n-gram language models using maximum likelihoo Building scalable n-gram language models using maximum likelihoo

1995-06-07

1997-06-17

Sheikh, Ayaz R.

395 249, 395 264, G10L 900, G10L 506

Patent

active

056404875

ABSTRACT:
The present invention is an n-gram language modeler which significantly reduces the memory storage requirement and convergence time for language modelling systems and methods. The present invention aligns each n-gram with one of "n" number of non-intersecting classes. A count is determined for each n-gram representing the number of times each n-gram occurred in the training data. The n-grams are separated into classes and complement counts are determined. Using these counts and complement counts factors are determined, one factor for each class, using an iterative scaling algorithm. The language model probability, i.e., the probability that a word occurs given the occurrence of the previous two words, is determined using these factors.

REFERENCES:
patent: 4817156 (1989-03-01), Bahl et al.
patent: 4831550 (1989-05-01), Katz
patent: 5293584 (1994-03-01), Brown et al.
patent: 5467425 (1995-11-01), Lau et al.
Bahl, Lalit R., Frederick Jelinek and Robert L. Mercer, "A Maximum Likelihood Approach to Continuous Speech Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, Mar. 1983, pp. 179-190.
Ney et al., "On Smoothing Techniques for Bigram-Based Nayural Language Modelling", ICASSP '91, 1991, pp. 825-828.
Passeler et al., "Continuous-Speech Recognition Using a Stochastic Language Model", ICASSP '89, 1989, pp. 719-722.
Jelinek et al., "Classifying Words for Improved Statistical Language Models", ICASSP '90. 1990, pp. 621-624.

Affiliated with

Also associated with

Rating

Building scalable n-gram language models using maximum likelihoo does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Building scalable n-gram language models using maximum likelihoo, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Building scalable n-gram language models using maximum likelihoo will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2164296