公开(公告)号：US20190155909A1

公开(公告)日：2019-05-23

申请号：US16007073

申请日：2018-06-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hwidong NA

IPC: G06F17/28

Abstract: A machine translation method includes translating a source sentence using a first model, determining a back-translation probability of a translation result of the source sentence being back-translated into the source sentence using a second model, applying the back-translation probability to context information extracted from the source sentence in the first model, and retranslating the source sentence using the first model and the context information to which the back-translation probability is applied

公开(公告)号：US20190114540A1

公开(公告)日：2019-04-18

申请号：US16014779

申请日：2018-06-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik LEE ,  Hwidong NA

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/28 ,  G10L15/16 ,  G06F17/18

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：US20210081610A1

公开(公告)日：2021-03-18

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：US20180190268A1

公开(公告)日：2018-07-05

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 ,  G10L15/02 ,  G10L17/00 ,  G10L15/22

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：US20210406688A1

公开(公告)日：2021-12-30

申请号：US17469590

申请日：2021-09-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seongmin OK ,  Young-Seok KIM ,  Hwidong NA ,  Sanghyun YOO ,  Hoshik LEE ,  Junhwi CHOI

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A method and computing device with classification verification is provided. A processor-implemented method includes implementing a classification neural network to generate a classification result of data input to the classification neural network by generating, with respect to the input data, intermediate hidden values of one or more hidden layers of the classification neural network, generating the classification result of the input data based on the generated intermediate hidden values, and generating a determination of a reliability of the classification result by implementing a verification neural network, input the intermediate hidden values, to generate the determination of the reliability.

公开(公告)号：US20200073948A1

公开(公告)日：2020-03-05

申请号：US16371949

申请日：2019-04-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jihyun LEE ,  Hwidong NA

IPC: G06F17/28 ,  G06F17/27

Abstract: A sentence mapping method includes obtaining a source language document in a source language and a target language document in a target language, wherein the target language document is a translation of the source language document, generating a translated document by translating the target language document into the source language, and mapping source language sentences in the source language document and target language sentences with the target language document by comparing the source language document and the translated document.

公开(公告)号：US20180046618A1

公开(公告)日：2018-02-15

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: G06F17/28 ,  G06F17/30

CPC classification number: G06F17/2836 ,  G06F16/3344 ,  G06F17/2854 ,  G06F17/2863 ,  G06F17/289 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/08

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：US20230035351A1

公开(公告)日：2023-02-02

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

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：US20220374613A1

公开(公告)日：2022-11-24

申请号：US17865828

申请日：2022-07-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jihyun LEE ,  Hwidong NA ,  Hoshik LEE

IPC: G06F40/47 ,  G06N5/02 ,  G06F40/40 ,  G06F40/45 ,  G06F40/51

Abstract: A translation method includes: selecting a source word from a source sentence; generating mapping information including location information of the selected source word mapped to the selected source word in the source sentence; and correcting a target word, which is generated by translating the source sentence, based on location information of a feature value of the target word and the mapping information.

公开(公告)号：US20190051292A1

公开(公告)日：2019-02-14

申请号：US15838519

申请日：2017-12-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hwidong NA

IPC: G10L15/16 ,  G10L25/30 ,  G06N3/08 ,  G10L15/183 ,  G10L15/28

Abstract: A method and apparatus for training a recognition model and a recognition method and apparatus using the model are disclosed. The apparatus for training the model obtains an estimation hidden vector output from a hidden layer of the model in response to an estimation output vector output from the model at a previous time being input into the model at a current time, and trains the model such that the estimation hidden vector of the current time matches an answer hidden vector output from the hidden layer in response to an answer output vector, corresponding to the estimation output vector of the previous time, being input into the model at the current time.