Patents by Inventor Jae Woong Yun
Jae Woong Yun has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240143927Abstract: Provided are a method for generating a summary and a system therefor. The method according to some embodiments may include calculating a likelihood loss for a summary model using a first text sample and a first summary sentence corresponding to the first text sample, calculating an unlikelihood loss for the summary model using a second text sample and the first summary sentence, the second text sample being a negative sample generated from the first text sample, and updating the summary model based on the likelihood loss and the unlikelihood loss.Type: ApplicationFiled: October 26, 2023Publication date: May 2, 2024Applicants: SAMSUNG SDS CO., LTD., SEOUL NATIONAL UNIVERSITY R&DB FOUNDATIONInventors: Sung Roh YOON, Bong Kyu HWANG, Ju Dong KIM, Jae Woong YUN, Hyun Jae LEE, Hyun Jin CHOI, Jong Yoon SONG, Noh II PARK, Seong Ho JOE, Young June GWON
-
Patent number: 11934950Abstract: 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.Type: GrantFiled: October 26, 2020Date of Patent: March 19, 2024Assignee: SAMSUNG SDS CO., LTD.Inventors: Seong Ho Joe, Young June Gwon, Seung Jai Min, Ju Dong Kim, Bong Kyu Hwang, Jae Woong Yun, Hyun Jae Lee, Hyun Jin Choi
-
Publication number: 20240020578Abstract: Methods and apparatuses for embedding data. The method for embedding data includes: acquiring a pretrained embedding model; generating a prompt associated with a data sample through a prompt encoder, the prompt encoder being lighter than the embedding model; generating an embedding representation of the data sample by inputting the prompt and the data sample to the embedding model; calculating a task loss by performing a predefined task by using the embedding representation; and updating the prompt encoder based on the task loss.Type: ApplicationFiled: July 13, 2023Publication date: January 18, 2024Applicant: SAMSUNG SDS CO., LTD.Inventors: Hyun Jae LEE, Hyun Jin CHOI, Jae Woong YUN
-
Publication number: 20230081042Abstract: An apparatus for processing natural language according to an embodiment includes a collection module that collects documents having tags, a parsing module that extracts text from the collected documents and extracts tag-related information on the tag surrounding each extracted text, and a preprocessing module that generates tokens of a preset unit by tokenizing each extracted text, generates token position information for each token in full text of the document, and sets the token and the token position information as training data in matching with the tag-related information.Type: ApplicationFiled: July 13, 2022Publication date: March 16, 2023Inventors: Bong-Kyu HWANG, Ju-Dong KIM, Jae-Woong YUN, Hyun-Jae LEE, Hyun-Jin CHOI, Seong-Ho JOE, Young-June GWON
-
Publication number: 20230046448Abstract: Disclosed are a method and system for changing a structure of a deep learning model based on a change in resolution of input data. The method of changing a structure of a deep learning model may include generating, by the at least one processor, a plurality of input data having different resolution by performing various resolution changes on input data having given resolution, performing, by the at least one processor, inference on each of the plurality of generated input data through a deep learning model, checking, by the at least one processor, the size of a feature map output by each of layers included in the deep learning model while the inference is performed, and changing, by the at least one processor, the structure of at least one of the layers based on the checked size of the feature map.Type: ApplicationFiled: August 11, 2022Publication date: February 16, 2023Applicant: NOTA, INC.Inventors: Byeongman LEE, Jae Woong YUN, Minsu KIM, Tae-Ho KIM
-
Publication number: 20220382793Abstract: An apparatus for training a document summarization model includes a token generation unit, a named entity recognition unit, and a model training unit. The token generation unit generates document tokens and summarization tokens. The named entity recognition unit assigns named entity token status to a summarization token, recognized as a named entity through NER, and assigns non-named entity token status to the other tokens. The model training unit obtains feature vectors by inputting the plurality of document tokens into an encoder inside a document summarization model, obtains a first loss related to the named entity token, a second loss related to the other tokens, and a total loss using a weighted value by inputting the feature vectors, the summarization tokens, the named entity token, and the non-named entity token into a decoder inside the document summarization model, and trains the document summarization model on the basis of the total loss.Type: ApplicationFiled: May 31, 2022Publication date: December 1, 2022Inventors: Bong-Kyu HWANG, Ju-Dong KIM, Jae-Woong YUN, Hyun-Jae LEE, Hyun-Jin CHOI
-
Publication number: 20220310075Abstract: 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.Type: ApplicationFiled: October 29, 2021Publication date: September 29, 2022Inventors: Hyun Jae LEE, Hyun Jin CHOI, Jae Woong YUN, Ju Dong KIM, Bong Kyu HWANG, Seong Ho JOE, Young June GWON
-
Publication number: 20210319260Abstract: 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.Type: ApplicationFiled: October 26, 2020Publication date: October 14, 2021Inventors: Seong Ho JOE, Young June GWON, Seung Jai MIN, Ju Dong KIM, Bong Kyu HWANG, Jae Woong YUN, Hyun Jae LEE, Hyun Jin CHOI
-
Publication number: 20210124976Abstract: An apparatus for calculating a similarity of images according to one embodiment includes a first feature extractor configured to extract an image feature vector from an image, a text region detector configured to detect one or more text object regions included in the image, a second feature extractor configured to extract a text image feature vector from each of the detected text object regions, a third feature extractor configured to recognize text from each of the text object regions and extract a text semantic feature vector from the recognized text, and a concatenator configured to generate a text object feature vector from the text image feature vector and the text semantic feature vector, which are extracted from the same text object region.Type: ApplicationFiled: October 28, 2019Publication date: April 29, 2021Inventors: JU-DONG KIM, Bong-kyu Hwang, Jae-woong Yun
-
Patent number: 10423297Abstract: A mobile terminal and controlling method thereof are disclosed, by which a selection and/or execution of an application can be designated using a list of applications currently executed in a multitasking environment. The present invention includes a display unit, a user input unit configured to receive an input of a command from a user, and a controller, when a plurality of applications are being executed, if there is a first input via the user input unit, controlling a list of a plurality of the currently executed applications to be displayed on a first region, the controller, if one of at least one or more applications running in the background in the list is selected by a second input via the user input unit, controlling the selected application to be displayed on a second region of the display unit by having a prescribed visual effect applied thereto.Type: GrantFiled: September 13, 2016Date of Patent: September 24, 2019Assignee: LG ELECTRONICS INC.Inventors: Jong Cheol Jung, Hong Joo Kim, Jae Woong Yun
-
Patent number: 10379786Abstract: A semiconductor device may include a data storage region, a parity storage region and an error correction circuit. The data storage region may be configured to store first data and second data. The parity storage region may be configured to store a parity. The error correction circuit may be configured to correct an error of the first data or an error of the second data and the parity, based on a transmission selection signal.Type: GrantFiled: September 7, 2016Date of Patent: August 13, 2019Assignee: SK hynix Inc.Inventors: Mun Seon Jang, Saeng Hwan Kim, Chang Ki Baek, Jae Woong Yun
-
Patent number: 10289485Abstract: An integrated circuit includes a first semiconductor device suitable for outputting a first error information signal by performing a first error correction operation, and a second semiconductor device suitable for outputting a second error information signal by performing a second error correction operation. The first error correction operation and the second error correction operation are performed simultaneously, and the second error information signal is outputted from the second semiconductor device after the first error information signal is outputted from the first semiconductor device.Type: GrantFiled: May 31, 2017Date of Patent: May 14, 2019Assignee: SK hynix Inc.Inventors: Jae Woong Yun, Yong Mi Kim, Chang Hyun Kim
-
Publication number: 20190126825Abstract: Provided are an apparatus and a method of compositing vehicle periphery images. The method of compositing vehicle periphery images includes selecting an object of interest from a rear image, adjusting a view area of the rear image based on the object of interest, and compositing a left image, the rear image, and a right image by reflecting a composite reference line according to the view area.Type: ApplicationFiled: August 13, 2018Publication date: May 2, 2019Applicant: SAMSUNG SDS CO., LTD.Inventors: Du Won PARK, Jae Woong YUN, Sun Jin KIM, Min Kyu KIM, Ki Sang KWON
-
Publication number: 20190095098Abstract: A semiconductor memory device may include a data-determining circuit and a memory cell array. The data-determining circuit may receive data to determine a majority level of data among the received data. The data-determining circuit may provide data bus inversion information to invert data of an address including a minority level of data. The memory cell array may store the data bus inversion information through a redundant bit line.Type: ApplicationFiled: February 1, 2018Publication date: March 28, 2019Applicant: SK hynix Inc.Inventor: Jae Woong YUN
-
Patent number: 10181863Abstract: A semiconductor system may be provided. The semiconductor system may include a first semiconductor device and a second semiconductor device. The first semiconductor device may be configured to perform an error correction operation. The second semiconductor device may be configured to perform an error correction operation. The semiconductor system may selectively operate the first or second semiconductor devices with regards to error correction operations based on a mode signal.Type: GrantFiled: February 10, 2017Date of Patent: January 15, 2019Assignee: SK hynix Inc.Inventors: Jae Woong Yun, Yong Mi Kim, Chang Hyun Kim
-
Publication number: 20180067801Abstract: An integrated circuit includes a first semiconductor device suitable for outputting a first error information signal by performing a first error correction operation, and a second semiconductor device suitable for outputting a second error information signal by performing a second error correction operation. The first error correction operation and the second error correction operation are performed simultaneously, and the second error information signal is outputted from the second semiconductor device after the first error information signal is outputted from the first semiconductor device.Type: ApplicationFiled: May 31, 2017Publication date: March 8, 2018Applicant: SK hynix Inc.Inventors: Jae Woong YUN, Yong Mi KIM, Chang Hyun KIM
-
Publication number: 20180032392Abstract: A DBI (Data Bus Inversion) controller may be provided. The DBI controller may include an address generation circuit configured to generate a DBI address from an input address. The DBI controller may include a DBI flag signal input and output (input/output) circuit configured to input/output a DBI flag signal in order to write the DBI flag signal to a memory cell corresponding to the DBI address or read the DBI flag signal from the memory cell corresponding to the DBI address, based on a command.Type: ApplicationFiled: April 14, 2017Publication date: February 1, 2018Applicant: SK hynix Inc.Inventors: Jae Woong YUN, Yong Mi KIM, Chang Hyun KIM
-
Publication number: 20170359084Abstract: A semiconductor system may be provided. The semiconductor system may include a first semiconductor device and a second semiconductor device. The first semiconductor device may be configured to perform an error correction operation. The second semiconductor device may be configured to perform an error correction operation. The semiconductor system may selectively operate the first or second semiconductor devices with regards to error correction operations based on a mode signal.Type: ApplicationFiled: February 10, 2017Publication date: December 14, 2017Applicant: SK hynix Inc.Inventors: Jae Woong YUN, Yong Mi KIM, Chang Hyun KIM
-
Publication number: 20170337105Abstract: A semiconductor device may include a data storage region, a parity storage region and an error correction circuit. The data storage region may be configured to store first data and second data. The parity storage region may be configured to store a parity. The error correction circuit may be configured to correct an error of the first data or an error of the second data and the parity, based on a transmission selection signal.Type: ApplicationFiled: September 7, 2016Publication date: November 23, 2017Inventors: Mun Seon JANG, Saeng Hwan KIM, Chang Ki BAEK, Jae Woong YUN
-
Publication number: 20170131869Abstract: A mobile terminal and controlling method thereof are disclosed, by which a selection and/or execution of an application can be designated using a list of applications currently executed in a multitasking environment. The present invention includes a display unit, a user input unit configured to receive an input of a command from a user, and a controller, when a plurality of applications are being executed, if there is a first input via the user input unit, controlling a list of a plurality of the currently executed applications to be displayed on a first region, the controller, if one of at least one or more applications running in the background in the list is selected by a second input via the user input unit, controlling the selected application to be displayed on a second region of the display unit by having a prescribed visual effect applied thereto.Type: ApplicationFiled: September 13, 2016Publication date: May 11, 2017Applicant: LG ELECTRONICS INC.Inventors: Jong Cheol JUNG, Hong Joo KIM, Jae Woong YUN