System and method for natural language generation

Data processing: speech signal processing – linguistics – language – Linguistics

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S009000, C704S004000

Reexamination Certificate

active

11195973

ABSTRACT:
A system, method and computer-readable medium for generating natural language utilizes a stochastic process to choose a derivation tree according to a predetermined grammar, such as 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 algorithms.

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.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

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

Rate now

     

Profile ID: LFUS-PAI-O-3858359

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.