US 12,216,664 B2
Refining training sets and parsers for large and dynamic text environments
Hiep Huu Nguyen, Seal Beach, CA (US)
Assigned to Ontocord, LLC, Dover, DE (US)
Filed by Ontocord, LLC, Dover, DE (US)
Filed on Feb. 11, 2023, as Appl. No. 18/108,584.
Application 18/108,584 is a continuation of application No. 17/244,694, filed on Apr. 29, 2021, granted, now 11,580,114.
Application 17/244,694 is a continuation of application No. 16/588,071, filed on Sep. 30, 2019, granted, now 11,023,471, issued on Jun. 1, 2021.
Application 16/588,071 is a continuation of application No. 15/724,581, filed on Oct. 4, 2017, granted, now 10,437,833, issued on Oct. 8, 2019.
Claims priority of provisional application 62/404,600, filed on Oct. 5, 2016.
Claims priority of provisional application 62/404,623, filed on Oct. 5, 2016.
Claims priority of provisional application 62/404,615, filed on Oct. 5, 2016.
Prior Publication US 2024/0020309 A1, Jan. 18, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 16/2457 (2019.01); G06F 40/211 (2020.01); G06N 3/02 (2006.01)
CPC G06F 16/24575 (2019.01) [G06F 40/211 (2020.01); G06N 3/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generalizing a parser for discourse assistance, comprising:
receiving a text pair that includes at least a first text sequence and a second text sequence;
receiving a parser that is to be generalized;
receiving at least one constraint that is associated with a manner of matching text;
constraint matching the first text sequence with the second text sequence using a plurality of constraints, wherein at least one of the plurality of the constraints is based on a similarity between a pair of text sequences;
extracting a frame-slot of a matched sequence based on the constraint matching of the first text sequence with the second text sequence;
generalizing the parser based on the generated frame-slot of the matched sequence; and
returning the parser for use in an automated conversation generation system for the discourse assistance.