• Journal of Korean Society of Archives and Records Management
• /
• v.10 no.2
• /
• pp.193-214
• /
• 2010

The multiple entity data model which contains metadata that associate two or more entities is applied recordkeeping metadata standard in recent years. This paper described and analyzed the recordkeeping metadata standard applying multiple entities such as ISO 23081, Australia recordkeeping metadata Standard, New Zealand recordkeeping metadata Standard, New South Wales recordkeeping metadata Standard, Queensland recordkeeping metadata Standard recordkeeping metadata Standard, South Australia recordkeeping metadata Standard, focusing on scope, the number of entities, category in entity, metadata elements. And shows some examples of relationship entity which is the key of multiple entity. As a result of the analysis, this paper suggests some consideration when recordkeeping metadata standard applying multiple entities is revised.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.4
• /
• pp.29-57
• /
• 2014

This study aims to develop a metadata schema for sports moving records based on a multiple entity model as an attempt to suggest an effective way to manage, retrieve, and utilize sports moving records. The multiple entity model consists of four entities - sports match, match contributors, moving records, and record management business - and metadata elements were developed for each entity. In addition, authority records for sports team and persons were created to ensure the consistency of terminology and provide rich contextual information. The suggested multiple entity model, metadata elements, and authority records for sports teams and persons were verified, modified, and expanded by a group of experts including a sports marketing expert and professors in the sports department.

• Journal of Industrial Technology
• /
• v.25 no.A
• /
• pp.123-131
• /
• 2005

Semantic object model has widely been recognized as an alternative data modeling approach to entity-relationship model for database system design. In this study, we have presented a semantic object model for intermediary type shopping mall consisting of multiple buyers and sellers. Essential processes and information with regard to the customer management, product management, price estimation, product order etc. have been considered for this study. Upon careful examination and analysis of them, a detailed semantic objects and attributes have been drawn and structured into semantic object diagrams. The final objects were converted into an entity-relationship diagram so that intuitive comparison could be made for relational database design. The results in this study may form a conceptual framework for both academic concerns and more complicated system applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.35-47
• /
• 2024

This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.61-65
• /
• 2006

This paper is concerned with a quantitative computational trust model which lakes into account multiple evaluation criteria and uses the recommendation from others in order to get the trust value for entities. In the proposed trust model, the trust for an entity is defined as the expectation for the entity to yield satisfactory outcomes in the given situation. Once an interaction has been made with an entity, it is assumed that outcomes are observed with respect to evaluation criteria. When the trust information is needed, the satisfaction degree, which is the probability to generate satisfactory outcomes for each evaluation criterion, is computed based on the outcome probability distributions and the entity's preference degrees on the outcomes. Then, the satisfaction degrees for evaluation criteria are aggregated into a trust value. At that time, the reputation information is also incorporated into the trust value. This paper presents in detail how the trust model works.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.3
• /
• pp.329-359
• /
• 2016

This study has developed standard metadata for intangible cultural heritages based on multiple entity model. By analyzing "Preservation and Promotion of Intangible Cultural Heritage Act", which was newly legislated in 2016, intangible cultural heritages archiving books, archival information resources and guidelines of organizations which conducted resources investigations, the transmission status of intangible cultural heritages, and the current status of intangible cultural heritage digital archiving and information services of related organizations, we obtained information lists required for intangible cultural heritages and took them into account in the process of selecting elements for intangible cultural heritage metadata. In addition, developing the intangible cultural heritage metadata based on the multiple entity model made it possible to provide comprehensive information by organically linking numerous sorts of information-with intangible cultural heritage information, which is the most essential, in the center, information on agents related to intangible cultural heritages, archival information resources information that they produce, and record management task information required to manage these archival information resources. By maintaining various relations of intangible cultural heritages and keeping the information up-to-date, the developed metadata is expected to provide rich contextual information on intangible cultural heritages in addition to the efficient management of information; and ultimately, make contribution to sustainably developing the value of intangible cultural heritages.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.243-248
• /
• 2019

Multi-Task Learning(MTL) is a training method that trains a single neural network with multiple tasks influences each other. In this paper, we compare performance of MTL Named entity recognition(NER) model trained with Korean traditional culture corpus and other NER model. In training process, each Bi-LSTM layer of Part of speech tagging(POS-tagging) and NER are propagated from a Bi-LSTM layer to obtain the joint loss. As a result, the MTL based Bi-LSTM model shows 1.1%~4.6% performance improvement compared to single Bi-LSTM models.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.633-642
• /
• 2006

In the Internet environment many interactions between many users and unknown users take place and it is usually rare to have the trust information about others. Due to the lack of trust information, entities have to take some risks in transactions with others. In this perspective, it is crucial for the entities to be equipped with functionality to accumulate and manage the trust information on other entities in order to reduce risks and uncertainty in their transactions. This paper is concerned with a quantitative computational trust model which takes into account multiple evaluation criteria and uses the recommendation from others in order to get the trust for an entity. In the proposed trust model, the trust for an entity is defined as the expectation for the entity to yield satisfactory outcomes in the given situation. Once an interaction has been made with an entity, it is assumed that outcomes are observed with respect to evaluation criteria. When the trust information is needed, the satisfaction degree, which is the probability to generate satisfactory outcomes for each evaluation criterion, is computed based on the empirical outcome outcome distributions and the entity's preference degrees on the outcomes. Then, the satisfaction degrees for evaluation criteria are aggregated into a trust value. At that time, the reputation information is also incorporated into the trust value. This paper also shows that the model could help the entities effectively choose other entities for transactions with some experiments in e-commerce.

• CELLMED
• /
• v.5 no.4
• /
• pp.27.1-27.6
• /
• 2015

Literatures and experimental studies have shown that Prunella has an effect on anti-hypertension, however, its components are complicated, so that it is still difficult to clear the specific roles of its various components in blood pressure regulation in. So we decide to systematically study the anti-hypertension mechanism of Prunella. We integrated multiple databases and constructed molecular interaction network between the chemical constituents of Prunella Vulgaris and hypertension based on entity grammar systems model. The network has 262 nodes and 802 edges. Then we infer the interactions between chemical compositions and disease targets to clarify the anti-hypertension mechanism. Finally, we found Prunella could influence hypertension by regulating apoptosis, cell proliferation, blood vessel development and vasoconstriction, etc. Thus this study provides reference for drug development and compatibility, and also gives guidance for health care at a certain extent.