US 11,836,452 B2
Multi-turn dialogue response generation using asymmetric adversarial machine classifiers
Oluwatobi Olabiyi, Arlington, VA (US); and Erik T. Mueller, Chevy Chase, MD (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Feb. 27, 2023, as Appl. No. 18/114,567.
Application 18/114,567 is a continuation of application No. 17/003,350, filed on Aug. 26, 2020, granted, now 11,663,419.
Application 17/003,350 is a continuation of application No. 16/997,090, filed on Aug. 19, 2020.
Prior Publication US 2023/0206009 A1, Jun. 29, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/35 (2020.01); G06F 40/47 (2020.01); G06F 40/20 (2020.01); G06N 3/088 (2023.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01)
CPC G06F 40/35 (2020.01) [G06F 18/2185 (2023.01); G06F 40/20 (2020.01); G06F 40/47 (2020.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating a response, comprising:
receiving communication data comprising a plurality of dialog sequences;
generating, by a generator of a generative adversarial network and based on context embedding and word embedding of the communication data, a plurality of responses, wherein each response in the plurality of responses comprises at least one keyword selected based on a maximum likelihood estimation of the at least one keyword in the communication data;
ranking, by at least one discriminator of the generative adversarial network and based on the context embedding and the word embedding, the plurality of responses;
selecting, by the at least one discriminator, an optimal response from among the ranked plurality of responses; and
transmitting the optimal response.
 
11. A computing device for generating responses, comprising:
a processor; and
a memory in communication with the processor and storing instructions that, when executed by the processor, cause the computing device to:
receive communication data comprising a plurality of dialog sequences;
generate, by the computing device comprising a generator of a generative adversarial network and based on context embedding and word embedding of the communication data, a plurality of responses, wherein each response in the plurality of responses comprises at least one keyword selected based on a maximum likelihood estimation of the at least one keyword in the communication data;
rank, by the computing device comprising at least one discriminator of the generative adversarial network and based on the context embedding and the word embedding, the plurality of responses;
select, by the at least one discriminator, an optimal response from among the ranked plurality of responses; and
transmit the optimal response.
 
18. A non-transitory machine-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
receiving communication data comprising a plurality of dialog sequences;
generating, by a generator of a generative adversarial network and based on context embedding and word embedding of the communication data, a plurality of responses, wherein each response in the plurality of responses comprises at least one keyword selected based on a maximum likelihood estimation of the at least one keyword in the communication data;
ranking, by at least one discriminator of the generative adversarial network and based on the context embedding and the word embedding, the plurality of responses;
selecting, by the at least one discriminator, an optimal response from among the ranked plurality of responses; and
transmitting the optimal response.