• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.4
• /
• pp.277-284
• /
• 2012

Named entity recognition (NER) technique can play a crucial role in extracting information from the web. While NER systems with relatively high performances have been developed based on careful manipulation of terms with a statistical model, term mismatches often degrade the performance of such systems because the strings of all the candidate entities are not known a priori. Despite the importance of lexical-level term mismatches for NER systems, however, most NER approaches developed to date utilize only the term string itself and simple term-level features, and do not exploit the semantic features of terms which can handle the variations of terms effectively. As a solution to this problem, here we propose to match the semantic concepts of term units in restaurant named entities (NEs), where these units are automatically generated from multiple resolutions of a semantic tree. As a test experiment, we applied our restaurant NER scheme to 49,153 nouns in Korean restaurant web pages. Our scheme achieved an average accuracy of 87.89% when applied to test data, which was considerably better than the 78.70% accuracy obtained using the baseline system.

• The Korean Journal of Archival Studies
• /
• no.33
• /
• pp.155-206
• /
• 2012

Interests in archives management are getting expanded from the public sector into the cultural and artistic field for the ten years after legislation of "Act on the Management of Public Archives" in 1999. However, due to lack of recognition on the importance of archives in the cultural and artistic field, it is rather frequent that information is kept scattered or archives are lost. As an example, absence of precise contract documents or notes of bestowal keeps people from locating great amount of cultural properties, and because of it these creative properties are in the risk of thefts, the closed-door auctioning, or trades in unofficial channels. As how a nation manages cultural and artistic creation inside the nation reflects its cultural level, it can be said that one of the indexes to notice the extent of a nation's cultural level is to take a look at how they are circulated. This study started from this point. Growing economy and rising interests in culture and art made the society more cognizant of the importance and value that visual artworks have, but the archives and information which are showing the context of these artworks and are produced in the course of social interaction are relatively disregarded because too much emphasis lies on the work itself. It is harder to find archives or documentations in Korea than in other advanced countries about the artists themselves or philosophical discourse on the background of the artworks. There is not so much interest to preserve the archives and information produced after the exhibition also, and they are used for no more than promotion or reference. Hereupon, the researcher recognized the importance of visual arts archives and believed that systemic management on them are high in need. And metadata is an essential way for the systemic management, as recently management on artworks or their archives are conducted using the system of the agencies even though they are not produced electronically. The objective of this study is to manage visual arts archives systematically by designing a data model reflecting traits of visual arts archives. Metadata are needed in the every course of archives from acquisition to management, preservation and application. Visual arts archives find its rich value only when a systemic relationship is established among information on artist, artwork and events including exhibition. By establishing a Multiple Entity Data Model, in which artworks, artists and events (exhibitions) make relationship all together, metadata for management on visual arts archive gets more efficiency and at the same time explanatory trait of the archive gets higher. For this reason we, in the study, tried to design a data model by setting each as an independent entities and designating relations between them, in order to find a way to manage visual arts archives more systematically.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.2
• /
• pp.121-132
• /
• 2005

There have been several efforts for the investigation of the formal development team which was formed in the IAI to develop a common 2D standard specification between ISO/STEP and IAI/IFC since 2002. As a result, a drafting model has been included in the IFC2.x2 model. However, to be used actively in the construction practice for construction drawing exchange, the IFC model should be extended to the paper space for multiple views, drawing output, and delivery of drawings. Therefore, in this paper, the methodology of relating STEP and IFC has been investigated and schema extension of paper space(drawing sheet, presentation view, view pipeline), complex entity(leader), and dimension(associative) have been achieved. The resulting, IFC model will enable a basic harmonization with KOSDIC. SCADEC, and STEP-CDS by retaining the current IFC architecture. In addition, IT systems for the construction industry can be beneficial from the developed data model.

• Journal of Korean Society of Archives and Records Management
• /
• v.20 no.1
• /
• pp.115-137
• /
• 2020

This study aims to examine the limitations of status that describe archives based on the Archival rules, and to propose a new method using the Records in Context - Conceptual model (RiC-CM) as a solution. Given this, the study conducted literature reviews and case studies. The solutions based on RiC-CM and its effects on the limitations of the existing environment are as follows. First, RiC-CM can describe multiple provenances about archives. This can be solved by defining individual records and provenances as "entity" and expressing their associations as relationships. The interrelation of entities alone can more accurately represent the information of provenances associated with a particular archive, making it easier to identify the overall context that makes records. Second, RiC-CM can link related files. Those that belong to a specific records group (fonds) can be resolved by assigning them to individual entities and making interrelation according to the context that makes records. This method makes it possible to serve information about the context that makes records. From the user's point of view, more options are available for searching records. Third, RiC-CM can link all relevant producer-made records related to a specific production organization. If organizations are related to each other, they can be defined as "entity," and their relationship can be expressed as "associated with." It helps to comprehensively examine the context of provenances. The findings of this study are expected to be used as a basis for future research on RiC-CM, in response to the paradigm shift for electronic records management systems.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.227-248
• /
• 2017

This paper introduces an integrated model for systematically constructing a linguistic resource database that can be used by machine learning-based biomedical information extraction systems. The proposed method suggests an orderly process of collecting and constructing dictionaries and training sets for both named-entity recognition and relation extraction. Multiple heterogeneous structures for the resources which are collected from diverse sources are analyzed to derive essential items and fields for constructing the integrated database. All the collected resources are converted and refined to build an integrated linguistic resource storage. In this paper, we constructed entity dictionaries of gene, protein, disease and drug, which are considered core linguistic elements or core named entities in the biomedical domains and conducted verification tests to measure their acceptability.

• Journal of information and communication convergence engineering
• /
• v.5 no.2
• /
• pp.144-149
• /
• 2007

Grid technologies make it possible for IT resources to be shared across organizational and security domains. The traditional identity-based access control mechanisms are unscalable and difficult to manage. Thus, we propose the FAS (Federation Agent Server) model which is composed of three modules: Certificate Conversion Module (CCM), Role Decision Module (RDM), and Authorization Decision Module (ADM). The proposed FAS model is an extended Role-Based Access Control (RBAC) model which provides resource access capabilities based on roles assigned to the users. FAS can solve the problem of assigning multiple identities to a shared local name in grid-map file and mapping the remote entity's identity to a local name manually.

• Journal of Korean Society of Archives and Records Management
• /
• v.19 no.1
• /
• pp.117-136
• /
• 2019

This study aims to suggest the ways of integrated services for Cultural Heritage Archives that belong to the Cultural Heritage Administration. To this end, the study analyzed the archives of major affiliated organizations of the Cultural Heritage Administration that manage and preserve Korean cultural assets. A cultural asset metadata based on the multiple entity model and applicable data link model standard was suggested for the integrated service of high-value-added cultural heritage information resources.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.1
• /
• pp.105-124
• /
• 2013

Metadata standardization of resources, having a heterogeneous metadata structure for each presidential archive and presidential library and museum is preferentially required for utilizing and sharing presidential records. An integrated operation model of metadata to manage various types of presidential records is then needed. The purpose of this study is to create a design principle of integrated metadata, and to suggest relationships and attributes of metadata, needed for developing integrated metadata operation system on presidential records. The design principle includes "creation of relationship among presidential records", "design of each entity, applicable multiple entity data model", "design to describe various types of presidential records", "design to reflect lifelong management on records of holding institutes", and "designing hybrid metadata for long term preservation". Metadata element set consists of elements for common attributes with all types of presidential records for a unique attribute for a specific presidential record and for reference information among different records related to the production of presidential records.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1491-1494
• /
• 2003

Video adaptation in response to dynamic resource conditions and user preferences is required as a key technology to enable universal multimedia access (UMA) through heterogeneous networks by a multitude of devices in a seamless way. Although many adaptation techniques exist, selections of appropriate adaptations among multiple choices are often ad hoc. To provide a systematic solution, we present a general conceptual framework to model video entity, adaptation, resource, utility, and relations among them. It allows for formulation of various adaptation problems as resource-constrained utility maximization. We apply the framework to a practical case of dynamic bit rate adaptation. Furthermore, we present a description tool, which has been accepted as a part of the MPEG-21 Digital Item Adaptation (DIA), along with a brief overview of the .elated descriptors to support terminal and network quality of service (QoS).