公开(公告)号：US20240143940A1

公开(公告)日：2024-05-02

申请号：US18544209

申请日：2023-12-18

Applicant: 42Maru Inc. ,  Korea Advanced Institute of Science and Technology

Inventor： Dong Hwan KIM ,  Sung Ju HWANG ,  Seanie LEE ,  Dong Bok LEE ,  Woo Tae JEONG ,  Han Su KIM ,  You Kyung KWON ,  Hyun Ok KIM

IPC: G06F40/35 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04

CPC classification number: G06F40/35 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04

Abstract: The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.

公开(公告)号：US20210166102A1

公开(公告)日：2021-06-03

申请号：US16699443

申请日：2019-11-29

Applicant: 42Maru Inc.

Inventor： Dong Hwan KIM ,  Woo Tae JEONG ,  Seanie LEE ,  Gilje SEONG

IPC: G06N3/00 ,  G06N20/00

Abstract: A method of generating a question-answer learning model through adversarial learning may include: sampling a latent variable based on constraints in an input passage; generating an answer based on the latent variable; generating a question based on the answer; and machine-learning the question-answer learning model using a dataset of the generated question and answer, wherein the constraints are controlled so that the latent variable is present in a data manifold while increasing a loss of the question-answer learning model.

公开(公告)号：US20230342620A1

公开(公告)日：2023-10-26

申请号：US18214301

申请日：2023-06-26

Applicant: 42Maru Inc.

Inventor： Dong Hwan KIM ,  Woo Tae JEONG ,  Seanie LEE ,  Gilje SEONG

IPC: G06N3/088 ,  G06N20/00 ,  G06N3/004 ,  G06F16/33 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06N3/088 ,  G06N20/00 ,  G06N3/004 ,  G06F16/3334 ,  G06F16/3346 ,  G06N3/08 ,  G06F16/3347 ,  G06N3/045

Abstract: A method of generating a question-answer learning model through adversarial learning may include: sampling a latent variable based on constraints in an input passage; generating an answer based on the latent variable; generating a question based on the answer; and machine-learning the question-answer learning model using a dataset of the generated question and answer, wherein the constraints are controlled so that the latent variable is present in a data manifold while increasing a loss of the question-answer learning model.