• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.7
• /
• pp.479-486
• /
• 2013

The data model that can be said as skeleton of the information system constitutes important 2 axles in the information system together with the process model. There is entity, properties, relation as key factors of the data model, and entity is the most fundamental factor in the data model, and thus total data model becomes vague if not deriving entity definitely. This study dealt with entity deduction only. Deducing methods of existing entity depended on experiences, task knowledge of designers and clear procedures were not suggested, so there were many difficulties in approaching them from beginners or unskilled persons. For giving helps in solving the problem, this study proposes entity- deducing procedures based on tasks that can derive entity with a systematic process at previously derived target businesses through suggested methods from advancing researches. And the study enabled proposing procedures on imaginary tasks to be applied, objecting to undergraduates who had not experiences on the data modeling, and then verified suggesting process through a similarity checking between best answers with deduced entity by students after taking impossible points of comparing existing methods with suggesting process into consideration. By doing so, deducing entity closely to the best answer was confirmed accordingly. Therefore, a fact could be confirmed that beginners were able to deduce entity closely to the best answer even if letting beginners who had not experiences on the data modeling be applied to unfamiliar tasks. Regarding researches on properties and relation deduction besides entity, this study leaves them to next time.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• Journal of the Korean Society for information Management
• /
• v.22 no.3 s.57
• /
• pp.289-306
• /
• 2005

As FRBR defines structural framework based on ER modeling for bibliographic data elements, an effective tool is required to implement FRBR model. In this paper, we present the implementation of FRBR model based on Topic Maps. To show the effectiveness of Topic Maps as the implantation language of FRBR, we implement FRBR model of MyongSungHwangHu by means of Topic Maps. We can ascertain that topic-association of Topic Maps conceptually harmonize with entity-relation of FRBR, which means that Topic Maps is suitable for the implementation of FRBR model.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.32-39
• /
• 2020

In the large-scale infrastructure of cloud environment, illegal access rights are frequently caused by sharing applications and devices, so in order to actively respond to such attacks, a strengthened access control system is required to prepare for each situation. We proposed an entity attribute-based access control(EABAC) model based on security level and relation concept. This model has enhanced access control characteristics that give integrity and confidentiality to subjects and objects, and can provide different services to the same role. It has flexibility in authority management by assigning roles and rights to contexts, which are relations and context related to services. In addition, we have shown application cases of this model in multi service environment such as university.

• 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.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.1
• /
• pp.12-22
• /
• 1995

When we integrate schema of distributed local databases, we mean entity integration as central concept of schema integration, and semantic of entity affects several factors. Thus the schema integration in distributed database environment starts from definition of domain relation among entity types of local schemas. Moreover, the domain relation defined by designer needs some works for confidence and validation of schema integration system. But this work was not presented in previous integration system. In this paper, we define object oriented integration for schema integration of local databases in distributed system environment, present models to verify validation on its integration, and implement the validation system.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.124-127
• /
• 2020

관계 추출은 문장에서 두 개의 엔티티가 주어졌을 때 두 개의 엔티티에 대한 의미적 이해를 통해 관계를 분류하는 작업이다. 이와 같이 관계 추출에서 관계를 분류하기 위해서는 두 개의 엔티티에 대한 정보가 필요하다. 본 연구에서는 관계 추출을 하기 위해 문장에서 엔티티들의 표현을 다르게하여 관계 추출의 성능을 비교 실험하였다. 첫번째로는 문장에서 [CLS] 토큰(Token)으로 관계를 분류하는 Standard 엔티티 정보 표현과 두번째로는 엔티티의 앞과 뒤에 Special Token을 추가하여 관계를 분류하는 Entity-Markers 엔티티 정보 표현했다. 이를 기반으로 문장의 문맥 정보를 학습한 사전 학습(Pre-trained)모델인 BERT-Large와 ALBERT-Large를 적용하여 실험을 진행하였다. 실험 결과 Special Token을 추가한 Entity-Markers의 성능이 높았으며, BERT-Large에서 더 높은 성능 결과를 확인하였다.

• Journal of the Korean Society for Railway
• /
• v.7 no.1
• /
• pp.20-25
• /
• 2004

Railroad geotechnical information management system was developed by using Web GIS and DB in this study. The standardization of railroad geotechnical information is progressed by classifying three groups as like basic informations, vibration informations along railway lines and design drawings. The basic informations consisted of basic and dynamic properties of soils, geophysical exploration and seismic survey/exploration. And the specification for 'human exposure to whole-body vibration' was adopted to construct the vibration informations along railway lines. The informations as like drawings and photographs were saved by changing to graphic files in the standardization of design drawings. In the case of standardization of geographical information, the topographical maps(NGIS, 1:5000) were primarily used as digital maps. Another digital maps(KRRI, 1:5000) and their geographical DB based on NGI code system were added on this maps. The standardized informations were used to construct their database. And railroad information management system was developed using Entity-Relation(ER) model which had a good feasibility for expansion and transition to other system in designing stage of database. This system consisted of layer selection, search and analysis of geotechnical informations and Zeus DB was adopted for GIS operating and user interface. This system could be a good tool for saving, searching and analyzing the geotechnical and geophysical informations. These DB systems would offered the basic informations to plans, design and construction of railroad lines etc. in practical use.

• Archives of design research
• /
• v.13 no.4
• /
• pp.67-76
• /
• 2000

Websites support various user activities in a wide range of contents domain and so they require different approach to extract principal design problems. In the point of media perspective on websites, this paper figures out the relationship between designer, user and website and discusses design factors of usability. It aims for the basic framework for interface design. In the media perspective website is an information entity mediating user and designer. Information entity is composed of various design factors relating to user, designer, website and others. It intends that user and information entity are accommodative to each other and have common conceptual model. To do so it is necessary for achieving usability objectives such as effectiveness, efficiency and satisfaction based on the understanding user goal, cognitive and affective characteristics. In the point of usability we examine design factors and features that are appropriate for users cognitive and affective function according to information entity model that constitutes contents, organization and representation level.