公开(公告)号：US11875119B2

公开(公告)日：2024-01-16

申请号：US17179178

申请日：2021-02-18

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sung Ju Hwang ,  Moonsu Han ,  Minki Kang ,  Hyunwoo Jung

IPC: G06F16/215 ,  G06N3/0442 ,  G06N5/00 ,  G06F40/30 ,  G06N20/00 ,  G06F18/21 ,  G06V10/776

CPC classification number: G06F40/30 ,  G06F18/217 ,  G06N20/00 ,  G06V10/776

Abstract: Provided is a memory-based reinforcement learning method and system capable of storing optional information in streaming data. A question-answering (QA) method using memory-based reinforcement learning method includes receiving, in an episodic memory reader (EMR), streaming data about an input context that is input from a user; analyzing, in the EMR, the received streaming data and storing preset semantic information used for QA in an external memory; and, in response to an input of a question front the user, determining, in a pretrained QA model, an answer to the input question based on semantic information stored in the external memory.

公开(公告)号：US20210263859A1

公开(公告)日：2021-08-26

申请号：US17179178

申请日：2021-02-18

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sung Ju Hwang ,  Moonsu Han ,  Minki Kang ,  Hyunwoo Jung

IPC: G06F12/121 ,  G06F40/30 ,  G06K9/62 ,  G06N20/00

Abstract: Provided is a memory-based reinforcement learning method and system capable of storing optional information in streaming data. A question-answering (QA) method using memory-based reinforcement learning method includes receiving, in an episodic memory reader (EMR), streaming data about an input context that is input from a user; analyzing, in the EMR, the received streaming data and storing preset semantic information used for QA in an external memory; and, in response to an input of a question from the user, determining, in a pretrained QA model, an answer to the input question based on sematic information stored in the external memory.