公开(公告)号：US11886817B2

公开(公告)日：2024-01-30

申请号：US17432446

申请日：2021-07-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyojung Han ,  Sathish Indurthi ,  Beomseok Lee ,  Mohd Abbas Zaidi ,  Nikhil Kumar

IPC: G06F40/284 ,  G06F40/58

CPC classification number: G06F40/284 ,  G06F40/58

Abstract: An electronic apparatus is disclosed. The electronic apparatus includes: an inputter comprising input circuitry configured to acquire an input sentence of a first language including a plurality of input tokens, a memory configured to store at least one instruction, and a processor, wherein the processor is configured to control the electronic apparatus to: acquire at least one first input token identified up to a first time point among the plurality of input tokens and acquire at least one first output token generated by translating the at least one first input token by inputting the at least one first input token and the at least one first output token into a learned first neural network model, identify an operation to be performed at a second time point after the first time point among a first operation configured to identify at least one second input token other than the at least one first input token among the plurality of input tokens and a second operation configured to generate at least one second output token based on the at least one first input token, and acquire a number corresponding to the identified operation and acquiring an output sentence of a second language different from the first language by translating the input sentence based on the identified operation and the acquired number.

公开(公告)号：US11604931B2

公开(公告)日：2023-03-14

申请号：US17030934

申请日：2020-09-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoonjin Yoon ,  Yoonjung Choi ,  Indong Lee ,  Hyojung Han

IPC: G06F40/58 ,  G06F40/44 ,  G06F40/47

Abstract: An electronic device is provided. The electronic device includes a memory and a processor. The processor is configured to, based on acquiring a first sentence in a first language, determine whether to correct the first sentence to another sentence in the first language by using a second language model trained based on a learning corpus, and based on determining to correct the first sentence to another sentence in the first language, input the first sentence into a conversion model trained to acquire another sentence having a similarity greater than or equal to a threshold value to an input sentence and acquire a second sentence in the first language which is a corrected form of the first sentence, and based on acquiring the second sentence, input the second sentence into a translation model trained based on the learning corpus and acquire a third sentence in a second language.

公开(公告)号：US11551675B2

公开(公告)日：2023-01-10

申请号：US16899987

申请日：2020-06-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sathish Reddy Indurthi ,  Hyojung Han ,  Beomseok Lee ,  Insoo Chung ,  Nikhil Kumar Lakumarapu

IPC: G10L15/183 ,  G10L15/26 ,  G10L15/16

Abstract: An electronic device is provided. The electronic device includes a memory configured to store a speech translation model and at least one processor electronically connected with the memory. The at least one processor is configured to train the speech translation model based on first information related to conversion between a speech in a first language and a text corresponding to the speech in the first language, and second information related to conversion between a text in the first language and a text in a second language corresponding to the text in the first language, and the speech translation model is trained to convert a speech in the first language into a text in the second language and output the text.

公开(公告)号：US12112140B2

公开(公告)日：2024-10-08

申请号：US17666127

申请日：2022-02-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Beomseok Lee ,  Hyojung Han ,  Sathish Indurthi ,  Mohd Abbas Zaidi ,  Nikhil Kumar

IPC: G06F40/58 ,  G06F3/16 ,  G06F40/289 ,  G10L13/02

CPC classification number: G06F40/58 ,  G06F3/165 ,  G06F40/289 ,  G10L13/02

Abstract: An electronic device includes a memory storing at least one instruction, and a processor configured to execute the at least one instruction to: input a first text into a first neural network model and acquire a first translation text; input the first translation text into a second neural network model and acquire a first liberal translation text; identify whether the first liberal translation text is to be outputted based on the first text and the first liberal translation text; output the first liberal translation text according to the identification result; based on a second text being received subsequently to the first text, input the first and second texts into the first neural network model and acquire a second translation text; and input the identification result and the second translation text into the second neural network model and acquire a second liberal translation text corresponding to the second translation text.

公开(公告)号：US11928111B2

公开(公告)日：2024-03-12

申请号：US17739453

申请日：2022-05-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yoonjung Choi ,  Jisang Yu ,  Hyojung Han ,  Jonghyun Kim ,  Hejung Yang

IPC: G06F16/2452 ,  G06N3/02

CPC classification number: G06F16/2452 ,  G06N3/02

Abstract: A method for controlling an electronic apparatus includes: translating a first query text of a first language to acquire a second query text of a second language; transmitting the second query text to an external device; acquiring, from the external device, a first response text of the second language in response to the second query text; acquiring a second response text acquired by translating the first response text into the first language, and identifying whether the second response text semantically matches to the first query text by inputting the second response text and the first query text into a first neural network model configured to identify whether a query and a response semantically match; and acquiring a third query text of the second language by retranslating the first query text based on a result of identifying that the first query text and the second response text do not semantically match.