摘要:
A method for stabilizing a knowledge graph includes: generating a knowledge graph in which same entities in a semantic relation list between entities provided as an input are represented as a single node based on names and types of the entities; computing, on the knowledge graph, semantic similarities between all potential entity pairs of same entity types by comparing, for each potential entity pair, a type of relation associated with an entity in the entity pair and an opponent entity to the entity; and selecting, based on the semantic similarities, a representative entity from each of semantically similar entity pairs on the knowledge graph and integrating an opponent entity to the representative entity into the representative entity. The method further includes computing relation weighted values between the entities by using a graph analysis and statistic information, and adding the weighted values to the knowledge graph.
摘要:
Provides is an apparatus for question answering based on answer trustworthiness including: an answer indexer that indexes documents of which document trustworthiness satisfying a threshold value among documents included in a document collection and stores it in a knowledge Bases; an answer candidate extractor that extracts answer candidate documents for a user's question from the knowledge Bases; an answer source trustworthiness measurement unit; an answer extraction strategy trustworthiness measurement unit; and a trustworthiness integrator that generates an answer candidate trustworthiness list by ranking the answer candidate documents on the basis of the document trustworthiness, the source trustworthiness, and the extraction strategy trustworthiness of the answer candidate documents.
摘要:
Disclosed is an apparatus and method for expressing a query for searching multimedia data. The apparatus and method of the present invention expresses diverse query types in MPEG-7 query formats and uses field types to re use a designated region. The apparatus for expressing a query inputted from a user for multimedia data search includes: an input means for receiving a query for multimedia data search from a user; and a query expression means for expressing the input query in a field type, wherein the field type includes at least one among identifier information indicating identification (ID) information of a field presenting a search condition included in the input query; type information indicating data type information of the field; and reference information indicating identifier information of another field for reference. The present invention is applied to MPEG-7 query formats.
摘要:
An electronic document processing apparatus includes: a document set storage unit storing hash tables including hash values of documents to be processed; a content extraction unit for extracting body contents from a newly input electronic document; and a sentence separation unit for separating sentences from the extracted body contents. The apparatus further includes a duplicate document determination unit for converting the separated sentences into unique hash values by a hash algorithm, determining each of the separated checking if there is a duplicate sentence depending on whether or not there is a collision between the converted hash values and the hash values in the hash tables of the document set storage unit, and determining if the electronic document is a duplicate document based on the ratio of duplicate sentences to all of the sentences in the electronic document.
摘要:
A personalized search apparatus includes: a model generating unit for generating a user favorites analysis model based on directory grouping information about directories stored in a user terminal and user behavior information; and a user favorites analysis model DB for storing the generated user favorites analysis model. Further, the personalized search apparatus includes a search engine for searching for a file relevant to an input query using an information search engine installed in the user terminal to generate search results; and a personalized search engine for re-ranking the search results generated by the search engine based on the user favorites analysis model to generate personalized search results.
摘要:
A method for social tagging using a property field of an ontology object includes: selecting an object in an ontology database storing therein objects in forms of classes; selecting a property field in a class corresponding to the selected object; and adding a social tag by storing user's input as a value of the selected property field. Classes stored in the ontology database may have property fields defined when instances of the classes are created, and specific values may be stored as values of the property fields also when the instances are created. The property fields defined when the instances are created are classified into data type property fields and object type property field, and the selected property field is a data type property field.
摘要:
Provided are an apparatus and method for searching multimedia data based on metadata. The apparatus for searching multimedia data includes: a mapping information storing unit for storing and managing mapping information between a Moving Picture Experts Group 7 (MPEG-7) query attribute and an MPEG-7 metadata property; and a query attribute mapping unit for acquiring the MPEG-7 metadata property to be mapped with the MPEG-7 query attribute according to a user query based on the mapping information.
摘要:
Disclosed is an apparatus and method for retrieving multimedia contents represented in a Moving Picture Experts Group (MPEG) 7 by transforming a user query into an MPEG-7 query format. The method for retrieving multimedia contents includes: representing a user query by using an indicator indicating a specific region of a Moving Picture Experts Group 7 (MPEG-7) document and a reference for referring to the indicator; analyzing a meaning of the user query represented by using the indicator and the reference to thereby produce an analysis result; and retrieving multimedia contents according to the analysis result. The present research can satisfy more than two retrieval conditions within the same structure in an MPEG-7 query format and it can also clearly represent that two different MPEG-7 documents are referred to. Since the meaning of a user query is analyzed accurately during retrieval process, it is possible to precisely retrieve multimedia contents.
摘要:
A method for stabilizing a knowledge graph includes: generating a knowledge graph in which same entities in a semantic relation list between entities provided as an input are represented as a single node based on names and types of the entities; computing, on the knowledge graph, semantic similarities between all potential entity pairs of same entity types by comparing, for each potential entity pair, a type of relation associated with an entity in the entity pair and an opponent entity to the entity; and selecting, based on the semantic similarities, a representative entity from each of semantically similar entity pairs on the knowledge graph and integrating an opponent entity to the representative entity into the representative entity. The method further includes computing relation weighted values between the entities by using a graph analysis and statistic information, and adding the weighted values to the knowledge graph.
摘要:
An apparatus and method for efficiently constructing learning data required in statistical methodology used in information retrieval, information extraction, translation, natural language processing, etc. are provided. The method includes the steps of: generating learning models by performing machine learning with respect to learning data; attaching tags to a raw corpus automatically by using the generated learning models to thereby generate learning data candidates; calculating confidence scores of the generated learning data candidates, and then selecting a learning data candidate using the confidence scores; and allowing a user to correct an error in the selected learning data candidate through an interface and adding the error-corrected learning data candidate to the learning data, thereby adding new learning models incrementally.