公开(公告)号：US20240394476A1

公开(公告)日：2024-11-28

申请号：US18674218

申请日：2024-05-24

Applicant: SAMSUNG SDS CO., LTD. ,  SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION

Inventor： Sung Roh YOON ,  Bong Kyu Hwang ,  Jae Woong Yun ,  Seong Ho Joe ,  Jong Yoon Song ,  Noh II Park ,  Young June Gwon

IPC: G06F40/284 ,  G06F40/295

Abstract: A method for generating a summary performed by at least one computing device is provided. The method may include: acquiring a first sample pair, the first sample pair including an original text and a summary corresponding to the original text, extracting a common phrase that appears simultaneously in the original text and the summary of the first sample pair, selecting a first phrase among common phrases based on a prediction probability of a summary model for the common phrases, generating a second sample pair by modifying the first phrase in the original text and the summary of the first sample pair, and updating the summary model by performing a summary task using the second sample pair.

公开(公告)号：US20240037347A1

公开(公告)日：2024-02-01

申请号：US18227745

申请日：2023-07-28

Applicant: SAMSUNG SDS CO., LTD.

Inventor： Jae Young Lee ,  Seong Ho Joe

IPC: G06F40/47 ,  G06N20/00

CPC classification number: G06F40/47 ,  G06N20/00

Abstract: Provided is a embedding transformation method performed by at least one computing device. The method comprises obtaining a source-side embedding model, transforming source-side data into a first embedding vector through the source-side embedding model and transforming the first embedding vector into a second embedding vector located in a target-side embedding space through a transformation model.

公开(公告)号：US12062365B2

公开(公告)日：2024-08-13

申请号：US17514338

申请日：2021-10-29

Applicant: SAMSUNG SDS CO., LTD.

Inventor： Hyun Jae Lee ,  Hyun Jin Choi ,  Jae Woong Yun ,  Ju Dong Kim ,  Bong Kyu Hwang ,  Seong Ho Joe ,  Young June Gwon

IPC: G10L15/18 ,  G06F40/35 ,  G10L15/06 ,  G10L15/22

CPC classification number: G10L15/18 ,  G10L15/063 ,  G10L15/22 ,  G10L2015/223

Abstract: An apparatus for training a dialogue summary model according to an embodiment includes a parameter transferer configured to transfer one or more learning parameter values of a pre-trained natural language processing model to a sequence-to-sequence-based dialogue summary model, and a model trainer configured to train the dialogue summary model by using the transferred learning parameter values as initial values for learning parameters of each of an encoder and a decoder in the dialogue summary model.

公开(公告)号：US11934950B2

公开(公告)日：2024-03-19

申请号：US17080351

申请日：2020-10-26

Applicant: SAMSUNG SDS CO., LTD.

Inventor： Seong Ho Joe ,  Young June Gwon ,  Seung Jai Min ,  Ju Dong Kim ,  Bong Kyu Hwang ,  Jae Woong Yun ,  Hyun Jae Lee ,  Hyun Jin Choi

IPC: G06N3/08 ,  G06F18/213 ,  G06N3/045 ,  G06N20/20 ,  G06F18/22

CPC classification number: G06N3/08 ,  G06F18/213 ,  G06N3/045 ,  G06N20/20 ,  G06F18/22

Abstract: An apparatus for embedding a sentence feature vector according to an embodiment includes a sentence acquisitor configured to acquire a first sentence and a second sentence, each including one or more words; a vector extractor configured to extract a first feature vector corresponding to the first sentence and a second feature vector corresponding to the second sentence by independently inputting each of the first sentence and the second sentence into a feature extraction network; and a vector compressor configured to compress the first feature vector and the second feature vector into a first compressed vector and a second compressed vector, respectively, by independently inputting each of the first feature vector and the second feature vector into a convolutional neural network (CNN)-based vector compression network.