Abstract:
Provided are an opinion analyzing system and method that analyze an opinion change based on an elapse of time and provide an analysis result. The opinion analyzing system includes a user terminal configured to transmit an opinion analysis request signal including an opinion analysis target keyword and analysis target period information, and an opinion analyzing server configured to, when the opinion analysis request signal is received from the user terminal, collect text information including the opinion analysis target keyword from a database according to the opinion analysis request signal, and analyze the collected text information to generate a summary text of an opinion.
Abstract:
An apparatus for managing risk in social web media in a prediction-based manner is provided, and includes a risk vocabulary management unit, which extracts and manages vocabulary to be managed as pertaining to risk from social web content, a risk issue prediction analysis quality extraction unit, which performs language analysis and sensitivity analysis, a risk prediction modeling unit, which models risk prediction analysis, a risk detection and notification unit, which automatically detects and notifies the risk, a risk situation monitoring unit, which monitors in real time a risk state of a risk entity when an alarm is raised with respect to the detected risk, and a risk history management unit, which receives user feedback for monitored risk information and manages a record of a terminated risk situation.
Abstract:
The present disclosure relates to an apparatus for outputting a language model from which a bias has been removed. The apparatus according to the present disclosure includes a bias estimation model configured to estimate a bias of text to be generated, a bias determination unit configured to determine a bias of next text to be generated through the bias estimation model, and a deep learning-based text generation model configured to generate the next text based on a result of the determination of the bias of the next text.
Abstract:
Provided is a system for creating a news article containing an indirect advertisement, the system including an advertisement database including an advertisement item and an indirect advertisement composed of text matching the advertisement item, an advertisement search unit configured to, when a text-type original news article to be exposed to a webpage is input, search the database for an indirect advertisement candidate matching the original news article and select an advertisement candidate list, an advertisement position determination unit configured to determine a paragraph of the original news article into which a selected advertisement is to be inserted, and an advertisement phrase creation unit configured to create a news article containing an advertisement by inserting the selected advertisement into the paragraph of the original news article and expose the created news article.
Abstract:
An apparatus and method for customer interaction service is provided. The apparatus for customer interaction comprises a customer interaction information DB configured to map voice of customer(VOC) with customer interaction information responding to the VOC by a service provider and store the result; a VOC collecting unit configured to collect VOC in a text or voice form; a VOC analyzing unit configured to extract target texts to be analyzed from the collected VOC and analyze the extracted text to provide analysis result including the subject of VOC; an interaction information searching unit configured to search VOC related to the collected VOC from the customer interaction information DB by using the analysis result; and a response providing unit configured to determine suitability of each customer interaction information related to the collected VOC to provide the best response to the customer based on the determined suitability.
Abstract:
The present invention is to provide an apparatus for searching information based on Wikipedia's contents comprising: a document converting part extracting fulltext documents, section title documents, info-box documents, category documents and definition statement documents from Wikipedia original documents and generating at least one of Wikipedia documents for questions and answers; a document indexing part analyzing the Wikipedia document for questions and answers, extracting POS-based index terms from the Wikipedia document for questions and answers, and generating a Wikipedia document index for questions and answers; a question analyzing part receiving a natural language question, analyzing a question pattern, an answer pattern and a question focus from the natural language question, and extracting document search keywords; a document searching part performing document search by using the document search keywords from the Wikipedia document index for questions and answers and generating document search result from each Wikipedia document index for questions and answers; an answer extracting part extracting first answers by using information about the question pattern, the answer pattern and the question focus from the document search result; and an answer integrating part integrating and prioritizing the first answer and generating a second answer.
Abstract:
Provided is a method of providing a shared neural model by a question-answering system, the method including: learning a shared neural model on the basis of initial model learning data; providing a plurality of user terminals with the shared neural model upon completing the learning of the shared neural model; upon the user terminal updating the shared neural model to a personalized neural model, collecting the updated personalized neural model; updating the shared neural model on the basis of the collected personalized neural model; and providing the updated shared neural model to the plurality of user terminals.
Abstract:
An apparatus for amending a language analysis error includes: a main language analyzer, which includes a plurality of language processing modules being sequentially connected to each other, and generates one best main analysis result for each processing module; a subsidiary language analyzer, which includes the plurality of language processing modules, and generates a plurality of subsidiary analysis results for each of the plurality of language processing modules; and an analysis result amender to in response to an error occurring in the main analysis result, acquire a subsidiary analysis result, and transmit the subsidiary analysis result to the main language analyzer.
Abstract:
An apparatus and method for updating a language analysis result are provided. The apparatus includes a storage unit configured to store language analysis result and language analysis metadata to be used for update of the language analysis result, and an update unit configured to reanalyze the language analysis metadata based on language knowledge which is added to language knowledge resources, and update the language analysis result based on the reanalyzed result.
Abstract:
Disclosed is a method of representing user language characteristics in a MPEG user description (MPEG-UD) system including receiving a request for a user description (UD) of the user language characteristics from a recommendation engine, calling the UD of the user language characteristics from a UD database, and transmitting the called UD of the user language characteristics to the recommendation engine.