Probabilistic model for natural language generation

Details Probabilistic model for natural language generation Probabilistic model for natural language generation

2005-09-20

2005-09-20

McFadden, Susan (Department: 2655)

Data processing: speech signal processing, linguistics, language

Linguistics

C704S004000, C704S009000

Reexamination Certificate

active

06947885

ABSTRACT:
A natural language generator utilizes a stochastic process to choose a derivation tree according to a predetermined reference grammar, such as a tree-adjoined grammar (TAG). A word lattice is created from a single semi-specified derivation tree and the proper path (i.e., desired output string) is selected from the lattice using a least cost, or other appropriate algorithm.

REFERENCES:
patent: 5237502 (1993-08-01), White et al.
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5526479 (1996-06-01), Barstow et al.
patent: 5721939 (1998-02-01), Kaplan
patent: 5754736 (1998-05-01), Aust
patent: 5761637 (1998-06-01), Chino
patent: 5774525 (1998-06-01), Kanevsky
patent: 5930746 (1999-07-01), Ting
patent: 5963894 (1999-10-01), Richardson
patent: 5987404 (1999-11-01), Della Pietra et al.
patent: 6044347 (2000-03-01), Abella et al.
patent: 6128634 (2000-10-01), Golovchinsky et al.
patent: 6163769 (2000-12-01), Acero et al.
patent: 6169972 (2001-01-01), Kono et al.
patent: 6789231 (2004-09-01), Reynar et al.

Affiliated with

Also associated with

Rating

Probabilistic model for natural language generation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Probabilistic model for natural language generation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Probabilistic model for natural language generation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3396002