公开(公告)号：US11727275B2

公开(公告)日：2023-08-15

申请号：US17950521

申请日：2022-09-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hwidong Na ,  Hyohyeong Kang ,  Hogyeong Kim ,  Hoshik Lee

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A model training method and apparatus is disclosed, where the model training method acquires a recognition result of a teacher model and a recognition result of a student model for an input sequence and trains the student model such that the recognition result of the teacher model and the recognition result of the student model are not distinguished from each other.

公开(公告)号：US11244671B2

公开(公告)日：2022-02-08

申请号：US16549236

申请日：2019-08-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hogyeong Kim ,  Hyohyeong Kang ,  Hwidong Na ,  Hoshik Lee

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/16 ,  G06N3/08

Abstract: A model training method and apparatus is disclosed, where the model training method acquires first output data of a student model for first input data and second output data of a teacher model for second input data and trains the student model such that the first output data and the second output data are not distinguished from each other. The student model and the teacher model have different structures.

公开(公告)号：US11182555B2

公开(公告)日：2021-11-23

申请号：US16844362

申请日：2020-04-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hwidong Na ,  Min-Joong Lee

IPC: G06F40/279

Abstract: A sequence processing method and apparatus are provided. The sequence processing method includes determining a word of a first R-node corresponding to a root node based on an input sequence, generating first I-nodes that are connected to the first R-node and include relative position information with respect to the word of the first R-node, determining a word of a second R-node to correspond to each of the first I-nodes, and determining an output sequence corresponding to the input sequence based on the determined words.

公开(公告)号：US10902216B2

公开(公告)日：2021-01-26

申请号：US15450333

申请日：2017-03-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hodong Lee ,  Youngki Park ,  Hwidong Na ,  Minyoung Mun ,  Inchul Song

IPC: G06F40/47 ,  G06F16/33 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06F40/51 ,  G06F40/53 ,  G06F40/58

Abstract: A translation method and apparatus may respectively perform or include: using one or more processors, plural different translation processes, in parallel, for a source sentence in a first language, including encoding, to generate respective feature vectors, the source sentence in each of two or more translation processes of the plural translation processes or the source sentence and a variation of the source sentence in respective translation processes of the plural translation processes, and decoding each of the respective feature vectors to generate respective plural candidate sentences in a second language; and selecting a final sentence in the second language from the respective plural candidate sentences in the second language.

公开(公告)号：US11727263B2

公开(公告)日：2023-08-15

申请号：US16014779

申请日：2018-06-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik Lee ,  Hwidong Na

IPC: G06N3/08 ,  G06F17/18 ,  G10L15/16 ,  G06F40/44 ,  G06F40/51 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06F17/18 ,  G06F40/44 ,  G06F40/51 ,  G06N3/045 ,  G10L15/16

Abstract: A processor implemented method to update a sentence generation model includes: generating a target sentence corresponding to a source sentence using a first decoding model; calculating reward information associated with the target sentence using a second decoding model configured to generate a sentence in an order different from an order of the sentence generated by the first decoding model; and generating an updated sentence generation model by resetting a weight of respective nodes in the first decoding model based on the calculated reward information.

公开(公告)号：US11151335B2

公开(公告)日：2021-10-19

申请号：US16445660

申请日：2019-06-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hwidong Na

IPC: G06F40/58 ,  G06N3/04 ,  G06F40/30 ,  G06F40/42 ,  G06F40/55 ,  G06F40/205

Abstract: A machine translation method includes using an encoder of a source language to determine a feature vector from a source sentence expressed in the source language, using an attention model of a target language to determine context information of the source sentence from the determined feature vector, and using a decoder of the target language to determine a target sentence expressed in the target language from the determined context information.

公开(公告)号：US11017294B2

公开(公告)日：2021-05-25

申请号：US15585377

申请日：2017-05-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hwidong Na

IPC: G06N3/08 ,  G06K9/66 ,  G06K9/46 ,  G06N3/04 ,  G10L25/30

Abstract: A method of recognizing input data includes determining a feature vector corresponding to an ensemble model from input data, based on the ensemble model, and recognizing the input data based on the feature vector. The ensemble model includes a first model and a second model having a structure that is the same as a structure of the first model.

公开(公告)号：US10713439B2

公开(公告)日：2020-07-14

申请号：US15471573

申请日：2017-03-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik Lee ,  Hwidong Na

IPC: G06F40/30 ,  G06N3/08 ,  G06N3/04 ,  G06F40/56 ,  G06F40/247

Abstract: A sentence generating apparatus includes an encoder configured to generate a first sentence embedding vector by applying trained result data to a first paraphrased sentence of an input sentence, an extractor configured to extract verification sentences in a preset range from the generated first sentence embedding vector, and a determiner configured to determine a similarity of the first paraphrased sentence to the input sentence based on comparing the verification sentences to the input sentence.

公开(公告)号：US10679612B2

公开(公告)日：2020-06-09

申请号：US15808324

申请日：2017-11-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik Lee ,  Hwidong Na

IPC: G10L15/16 ,  G10L21/038 ,  G10L15/22 ,  G10L17/00 ,  G10L15/02

Abstract: A speech recognizing method and apparatus is provided. A speech recognizing method, implementing a speech recognizing model neural network for recognition of a speech, includes determining an attention weight based on an output value output by at least one layer of the speech recognizing model neural network at a previous time of the recognition of the speech, applying the determined attention weight to a speech signal corresponding to a current time of the recognition of the speech, and recognizing the speech signal to which the attention weight is applied, using the speech recognizing model neural network.

公开(公告)号：US10599781B2

公开(公告)日：2020-03-24

申请号：US15254347

申请日：2016-09-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hwidong Na ,  Inchul Song ,  Hoshik Lee

IPC: G10L15/04 ,  G06F17/20 ,  G06F17/28 ,  G06F17/27 ,  G06N3/04 ,  G06N3/08 ,  G10L15/193 ,  G10L15/18

Abstract: An apparatus and method for evaluating quality of an automatic translation is disclosed. An apparatus for evaluating quality of automatic translation includes a converter which converts an automatic translation and a reference translation of an original text to a first distributed representation and a second distributed representation, respectively, using a distributed representation model and a quality evaluator which evaluates quality of automatic translation data based on similarity between the first distributed representation and the second distributed representation.