-
公开(公告)号:US20230359836A1
公开(公告)日:2023-11-09
申请号:US18219339
申请日:2023-07-07
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyojung HAN , Yoonjin YOON , Yoonjung CHOI , Sangha KIM , Seokchan AHN , Taehwan YOO , Beomseok LEE
IPC: G06F40/40
CPC classification number: G06F40/40
Abstract: An electronic device which obtains a first translated text in which a first phrase in an original text sequence of a first language is translated in a second language by inputting the first phrase to a translation model, determines an extent of delay in translation of the first phrase by comparing a time-point of the first phrase with a time-point of the first translated text, identifies one phrase from among the first phrase and a second phrase following the first phrase based on the extent of delay, obtains a summary text of the identified phrase by inputting the identified phrase to a summary model, obtains a second translated text in which identified phrase or the summary text is translated in the second language by inputting the identified phrase or the summary text to the translation model, and outputs the second translated text after the first translated text is output.
-
12.
公开(公告)号:US20230334739A1
公开(公告)日:2023-10-19
申请号:US18120717
申请日:2023-03-13
Applicant: Samsung Electronics Co., Ltd.
Inventor: Yoonjung CHOI , Jiyoung KANG , Chaekyung LEE , Yejin KIM
IPC: G06T11/60 , G06F3/03 , H04M1/02 , H04M1/72436 , G06T3/40
CPC classification number: G06T11/60 , G06F3/03 , H04M1/0241 , H04M1/72436 , G06T3/40 , H04M1/0214
Abstract: According to an embodiment, a processor of an electronic device identifies a plurality of subjects associated with the content, based on a request to display content within an active area of the display. The processor obtains a sequence of the plurality of subjects based on the plurality of subjects from the content. The processor displays a plurality of visual objects corresponding to each of the plurality of subjects based on the sequence and display the content according to a first magnification. The processor displays, among a first portion of the content corresponding to at least one subject selected based on the sequence among the plurality of subjects, or a second portion of the content different from the first portion, the first portion in the active area, based on a size of the active area controlled by the actuator by adjusting a magnification of the content to a second magnification.
-
公开(公告)号:US20220343156A1
公开(公告)日:2022-10-27
申请号:US17432631
申请日:2021-08-18
Applicant: Samsung Electronics Co., Ltd.
Inventor: Sangha KIM , Seokchan AHN , Yoonjung CHOI , Hakjung KIM , Yoonjin YOON
Abstract: A method performed by a server is provided. The method includes, in response to input information being processed by the first model in the terminal, receiving, from the terminal, intermediate data output from a first layer included in a shared portion of the first model, obtaining the first model and a second model, which are pretrained by including the shared portion, obtaining correct answer data for the input information by inputting the intermediate data as an output of the first layer to the first layer included in the shared portion of the second model, in response to the intermediate data being input as the output of the first layer to the first layer included in the shared portion of the first model, refining the first model so that the correct answer data may be output from the first model, and transmitting information about the refined first model to the terminal.
-
公开(公告)号:US20220284018A1
公开(公告)日:2022-09-08
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
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.
-
15.
公开(公告)号:US20210240942A1
公开(公告)日:2021-08-05
申请号:US17077874
申请日:2020-10-22
Applicant: SAMSUNG ELECTRONICS CO., LTD. , NEW YORK UNIVERSITY
Inventor: Yoonjung CHOI , Jaedeok KIM , Ilia KULIKOV , Sean WELLECK , Yuanzhe PANG , Kyunghyun CHO
IPC: G06F40/44 , G06F40/284 , G06F40/56
Abstract: A method of obtaining, by an electronic device, a sentence corresponding to context information, including obtaining first output information including at least one word output by decoding the context information based on at least one data; based on detecting that a first token is not included in the first output information, determining whether a number of words included in the first output information is greater than or equal to a reference value; based on a result of the determining, replacing the at least one data with other data; and obtaining the sentence corresponding to the context information based on at least one output information obtained by decoding the context information based on the other data.
-
-
-
-