Abstract: The invention relates to a method and a system for improving performance of text summarization and has an object of improving performance of a technique for generating a summary from a given paragraph. According to the invention to achieve the object, a method for improving performance of text summarization includes: an a step of generating an embedding vector by vectorizing a natural language-based context; a b step of generating a graph by using the embedding vector; a c step of assigning a weight depending on whether or not a keyword corresponding to at least one node included in the graph is present in the context; and a d step of selecting a path having a highest likelihood in the graph and generating a summary based on the path.

Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Abstract: A method of generating a question-answer learning model through adversarial learning may include: sampling a latent variable based on constraints in an input passage; generating an answer based on the latent variable; generating a question based on the answer; and machine-learning the question-answer learning model using a dataset of the generated question and answer, wherein the constraints are controlled so that the latent variable is present in a data manifold while increasing a loss of the question-answer learning model.

Abstract: The present disclosure relates to relay communication based on a sidelink in a wireless communication system, and a method for operating a first terminal may include performing direct communication with a second terminal based on a sidelink, when a path between the first terminal and the second terminal is predicted to be blocked and another relay device providing a relay service is discovered, transmitting, to the relay device, a first message for requesting the relay service for the first terminal and the second terminal, receiving, from the relay device, a second message for accepting the request for the relay service, and performing relay communication with the second terminal, and the first message may include information on the second terminal.

Abstract: A display device includes a first electrode and a second electrode which are disposed on a substrate and spaced apart from each other, a first insulating layer disposed on the first electrode and the second electrode, a light emitting element disposed on the first insulating layer, and having ends aligned on the first electrode and the second electrode, a first connection electrode disposed on the first electrode and electrically contacting an end of the light emitting element, a second connection electrode disposed on the second electrode and electrically contacting another end of the light emitting element, and a second insulating layer disposed on the first connection electrode and including a repair hole that exposes a portion of the first connection electrode.

Abstract: Disclosed are a rare-earth permanent magnet having improved magnetic properties and a method of manufacturing the same. A method of manufacturing a rare-earth permanent magnet may include: preparing a mixed powder including i) a first alloy represented by R1aR2bBcMdFebal and ii) a second alloy represented by R2bBcMdFebal where R1 is one or two or more of La, Ce, and Y; R2 is a rare-earth element except for La, Ce, and Y; and M is a metal element; press-forming and sintering the prepared mixed powder in a magnetic field to prepare a sintered body; and performing a heat treatment based on diffusion temperature conditions of an R1 component and an R2 component contained in the prepared sintered body.

Abstract: A touch sensor may include a substrate and may include electrode units, first demultiplexers, second demultiplexers, and driving pads all located on the substrate. The electrode units each may include a plurality of electrode groups, the electrode groups each including a plurality of touch electrodes. The first demultiplexers each may include a plurality of sub-demultiplexers and each may be electrically connected to a corresponding one of the electrode units. Each of the sub-demultiplexers of a first demultiplexer may be electrically connected to a corresponding one of the electrode groups of a corresponding electrode unit. The second demultiplexers may be connected between the first demultiplexers and the driving pads.

Abstract: An unstructured document analysis method according to an embodiment includes: operations of acquiring unstructured document data including font characteristic data and document structure data, extracting text included in the unstructured document data on the basis of the font characteristic data or the document structure data, classifying the extracted text into a pre-classified item using a trained neural network model, acquiring a content query related to the content included in the unstructured document data and associated with the pre-classified item, and generating an answer to the content query on the basis of the extracted text classified into the item.

Abstract: Provided are a device and method for converting a natural language query into a structured query language (SQL) query for a database search. The method includes an operation A of labeling natural language queries included in training data, an operation B of converting the natural language queries into second SQL queries by applying the natural language queries to an SQL conversion model, an operation C of verifying the second SQL queries, and an operation D of training the SQL conversion model by comparing the second SQL queries with third SQL queries corresponding to the natural language queries of the training data.

Abstract: Disclosed are a separator for fuel cells capable of minimizing the volume of a system and the use of sealants, and a stack for fuel cells, more particularly, a stack for solid oxide fuel cells, including the same. Specifically, by adding a metal sheet having a specific shape, position and size to the separator, the stress applied to the sealant can be uniformized, and thus the oxidizing agent and fuel can be separated and electrically isolated using only a piece of sealant. Therefore, the stack for fuel cells is characterized in that there is no variation in temperature, reactant concentration, power, or the like between respective unit cells, so delamination and microcracks do not occur, the volume is minimized, and the power density per unit volume is very high.

Abstract: A method of canceling road noise includes: receiving a first signal from an acceleration sensor disposed at a vehicle and a second signal from a microphone disposed at the vehicle; monitoring, based on the first and second signals, whether an abnormal event has occurred; determining, based on a result from monitoring whether the abnormal event has occurred, a plurality of parameter values for performing adaptive filtering; and performing, based on the determined parameter values, adaptive filtering to generating an output signal for noise canceling.

Abstract: An embodiment system for identifying a controller causing an electrical discharge of a vehicle includes a signal delay unit communicatively connected to controllers within the vehicle and configured to transmit a wake-up trigger signal after a predetermined first time passes when the wake-up trigger signal is input from a first controller among the controllers, and a microcontroller unit configured to enter into a wake-up mode after the first time passes when the microcontroller unit is in a sleep mode and the wake-up trigger signal is received through a single-channel transceiver connected to the first controller and store an identification of the first controller when the wake-up trigger signal is received from the signal delay unit.

Abstract: Provided are a computer system for transmitting audio content to realize a user-customized being-there and a method thereof. The computer system may be configured to detect audio files that are generated for a plurality of objects at a venue, respectively, and metadata including spatial features that are set for the objects at the venue, respectively, and to transmit the audio files and the metadata for a user. An electronic device of the user may realize a being-there at the venue by rendering the audio files based on the spatial features in the metadata. That is, the user may feel a user-customized being-there as if the user directly listens to audio signals generated from corresponding objects at a venue in which the objects are provided.

Abstract: Provided are method and apparatus for data structuring of text. The apparatus for data structuring of text includes a data extraction unit configured to extract text and location information of the text from an image based on an optical character recognition (OCR) technique, a data processing unit configured to generate a text unit based on the text and the location information, a form classification unit configured to classify a form of the image based on the text, a labeling unit configured to label the text unit as first text, second text, and third text respectively corresponding to an item name, an item value, or others based on the classified form, a relationship identification unit configured to map and structure the second text corresponding to the first text, and a misrecognition correction unit configured to determine misrecognition of the first text and correct the first text determined to be misrecognized.

Abstract: The present disclosure relates to an integrated circuit, a pixel driving device and a pixel defect detecting method and provides a device and method to sense a voltage of a light emitting diode of a pixel through a data line and to compare the sensed voltage with a reference range, thereby determining a pixel defect.

Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Abstract: The present invention relates to a vehicle frunk trim. A storage-box accommodation space is formed on one side of the frunk trim, and a flexible storage box is mounted on an inside surface of a sidewall, positioned in the direction of the storage-box accommodation space, of a body portion. For use, the storage box may extend to a desired length from the storage-box accommodation space. Articles is put in order outside the storage box and is stored in the storage box without unoccupied spaces in the storage box. Thus, a state where the articles are put in order is maintained, and noise due to collision between the articles is reduced.

Abstract: A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.

Abstract: A computer system for rendering event-customized audio content and a method thereof. The computer system may be configured to receive an event list of a plurality of events, an audio list for audio rendering information that matches each of the events, and event state information on a current event state, and to output current audio content according to audio rendering information that matches one of the events based on the current event state.

Abstract: An electric vehicle structure includes a drive system, a front lateral member and a rear upper lateral member. The front and rear lateral members are elongated in a lateral direction of a vehicle and spaced apart from each other in a forward-rearward direction of the vehicle with the drive system interposed therebetween. The vehicle structure further includes a rear lower lateral member elongated in the lateral direction of the vehicle and disposed beneath a motor of the drive system.