• 정보과학회 논문지
• /
• 제44권8호
• /
• pp.813-821
• /
• 2017

개체 링킹은 입력된 질의에 존재하는 개체를 표현한 개체 표현(entity mention)을 지식베이스에 존재하는 개체와 연결하여 의미를 파악하는 연구이다. 개체 링킹에 관한 연구는 지식 베이스 구축 문제, 다중 표현 문제, 개체 연결 중의성 문제, NIL 개체 인식 문제가 존재한다. 본 연구에서는 지식 베이스 구축 문제와 다중 표현 문제를 해결하기 위해 위키피디아를 기반으로 개체 이름 사전을 구축한다, 또한, 문맥 유사도, 의미적 관련성, 단서 단어 점수, 개체 표현의 개체명 타입 유사도, 개체 이름 매칭 점수, 개체인기도 점수 자질들을 기반으로 SVM(support vector machine)을 학습하여, NIL 개체를 인식하는 문제와 개체 연결 중의성을 해소하는 방법을 제안한다. 구축한 지식 베이스를 기반으로 제안한 두 방법을 순차적으로 적용하였을 때 좋은 개체 링킹 성능을 얻었다. 개체 링킹 시스템의 성능은 NIL 개체 인식 성능이 83.66%, 중의성 해소 성능이 90.81%의 F1 점수를 보였다.

• Journal of Computing Science and Engineering
• /
• 제8권3호
• /
• pp.137-148
• /
• 2014

Named entity classification of Wikipedia articles is a fundamental research area that can be used to automatically build large-scale corpora of named entity recognition or to support other entity processing, such as entity linking, as auxiliary tasks. This paper describes a method of classifying named entities in Chinese Wikipedia with fine-grained types. We considered multi-faceted information in Chinese Wikipedia to construct four feature sets, designed different feature selection methods for each feature, and fused different features with a vector space using different strategies. Experimental results show that the explored feature sets and their combination can effectively improve the performance of named entity classification.

• 인지과학
• /
• 제21권4호
• /
• pp.655-667
• /
• 2010

개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines(structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 대하여 기술하고 기존의 Conditional Random Fields(CRFs)를 이용한 시스템과의 성능을 비교한다. 실험결과 structural SVMs과 수정된 Pegasos 알고리즘이 기존의 CRFs 보다 높은 성능을 보였고(신뢰도 99%에서 통계적으로 유의함), structural SVMs과 수정된 Pegasos 알고리즘의 성능은 큰 차이가 없음(통계적으로 유의하지 않음)을 알 수 있었다. 특히 본 논문에서 제안하는 수정된 Pegasos 알고리즘을 이용한 경우 CRFs를 이용한 시스템보다 높은 성능(TV 도메인 F1=85.43, 스포츠 도메인 F1=86.79)을 유지하면서 학습 시간은 4%로 줄일 수 있었다.

• 무역상무연구
• /
• 제61권
• /
• pp.249-272
• /
• 2014

The purpose of this study is to seek the revitalization plans of export platform for supporting export enterprise of the domestic public services. To activate the export platform, alternatives to two aspects are required as follows. First of all, a governance plan of export platform should be established. At present, an operation entity of export platform, which is still developing stage, is not yet established. In this situation, even though export platform developed, it will faced with inefficient operation. Therefore, an operation entity and appropriate business model are important to the platform activation. second, to activate platform, it is necessary to support export process of life cycle. In particular, the service, which can support the business strategies setting and project implementation stage, is required. In addition, in order to activate the export platform is need to operate with he government's support program.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.218-221
• /
• 1996

전사적 데이터 모델을 개발하기 위해서는, 먼저, 기업에 있어서 중요하게 관리되어져야 할 주요 entity들을 파악하는 것이 선행되어야 한다. entity의 결정은 시스템 개발 전 단계에 걸쳐 지대한 영향을 끼치는 중요한 의사결정이나, 아직까지 이는 매우 주관적일 뿐 아니라 의사결정자의 경험 및 전문성에 매우 의존적이다. 또한 때로는 entity의 결정에 필요 이상의 많은 시간이 소요되기도 한다. 본 연구에서는 entity결정에 직면한 의사결정자를 지원하기 위하여, 사례기반 추론 기술을 채택한 의사결정지원시스템을 설계 개발하였다. 본 시스템에서는 과거에 성공적으로 entity를 결정했었다고 평가되는 사례로부터, 해당 기업의 상황에 적합한 새로운 결론을 도출해서 의사결정자를 효과적으로 지원한다.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.415-421
• /
• 2007

This paper proposes a convolution tree kernel-based approach for relation extraction where the parse tree is expanded with entity features such as entity type, subtype, and mention level etc. Our study indicates that not only can our method effectively capture both syntactic structure and entity information of relation instances, but also can avoid the difficulty with tuning the parameters in composite kernels. We also demonstrate that predicate verb information can be used to further improve the performance, though its enhancement is limited. Evaluation on the ACE2004 benchmark corpus shows that our system slightly outperforms both the previous best-reported feature-based and kernel-based systems.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권3호
• /
• pp.598-625
• /
• 2014

To support the procedure for determining an optimal liquefaction cycle for FLNG FEED, an ontological modeling method which can automatically generate various alternative liquefaction cycles were carried out in this paper. General rules in combining equipment are extracted from existing onshore liquefaction cycles like C3MR and DMR cycle. A generic relational model which represents whole relations of the plant elements has all these rules, and it is expressed by using the system entity structure (SES), an ontological framework that hierarchically represents the elements of a system and their relationships. By using a process called pruning which reduces the SES to a candidate, various alternative relational models of the liquefaction cycles can be automatically generated. These alternatives were provided by XML-based formats, and they can be used for choosing an optimal liquefaction cycle on the basis of the assessments such as process simulation and reliability analysis.

• 방재&안전
• /
• 제5권1호
• /
• pp.93-100
• /
• 2015

Although many years passed since 'The Legislative bill on the support of voluntary activities of enterprises for disaster reduction'(hereinafter referred to as 'enterprise disaster reduction act') has been first enacted in 2007, BCMS is still not activated in our society. In contrast, after 911 Terror, importance of BCM is getting magnified and standardization research & institutionalization i s a lso proceeding i all over world. Lately, Disaster preventing activities is urgently needed like the sinking of 'Sewol ferry'. So the purpose of this paper is proposed for establishment of 'BCMS' and activation of the certificate system for Best-Run Business by analyzing the problem of 'enterprise disaster reduction act' and weak of activation as following. First, propel changing the policy of self-regulated participation to mandatory about the certificate system for Best-Run Business from public entity to government ministry and it is able to activate by propelling demo business of the certificate system for Best-Run Business. Second, public entity that has been given the certificate system for Best-Run Business by affiliating with Disaster Management Assessment of government management can be exempted from Disaster Management Assessment or those entity can arrange for connectivity acquisition method of 'Excellent rate'. Third, to publicize the activation of the law mentioned above, makes public entity r ecognizable by incorporating 'BCMS' into National safety management plan and establishment of National critical infrastructures security plan. Fourth, it should be reviewed to improving the related act regarding to inclusion of public organizations as well as private enterprises.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.247-260
• /
• 2021

Data modeling is a process of developing a model to design and develop a data system that supports an organization's various business processes. A conceptual data model represents a technology-independent specification of structure of data to be stored within a database. The model aims to provide richer expressiveness and incorporate a set of semantics to (a) support the design, control, and integrity parts of the data stored in data management structures and (b) coordinate the viewing of connections and ideas on a database. The described structure of the data is often represented in an entity–relationship (ER) model, which was one of the first data-modeling techniques and is likely to continue to be a popular way of characterizing entity classes, attributes, and relationships. This paper attempts to examine the basic ER modeling notions in order to analyze the concepts to which they refer as well as ways to represent them. In such a mission, we apply a new modeling methodology (thinging machine; TM) to ER in terms of its fundamental building constructs, representation entities, relationships, and attributes. The goal of this venture is to further the understanding of data models and enrich their semantics. Three specific contributions to modeling in this context are incorporated: (a) using the TM model's five generic actions to inject processing in the ER structure; (b) relating the single ontological element of TM modeling (i.e., a thing/machine or thimac) to ER entities and relationships; and (c) proposing a high-level integrated, extended ER model that includes structural and time-oriented notions (e.g., events or behavior).

• Genomics & Informatics
• /
• 제18권2호
• /
• pp.15.1-15.6
• /
• 2020

Named entity recognition tools are used to identify mentions of biomedical entities in free text and are essential components of high-quality information retrieval and extraction systems. Without good entity recognition, methods will mislabel searched text and will miss important information or identify spurious text that will frustrate users. Most tools do not capture non-contiguous entities which are separate spans of text that together refer to an entity, e.g., the entity "type 1 diabetes" in the phrase "type 1 and type 2 diabetes." This type is commonly found in biomedical texts, especially in lists, where multiple biomedical entities are named in shortened form to avoid repeating words. Most text annotation systems, that enable users to view and edit entity annotations, do not support non-contiguous entities. Therefore, experts cannot even visualize non-contiguous entities, let alone annotate them to build valuable datasets for machine learning methods. To combat this problem and as part of the BLAH6 hackathon, we extended the TextAE platform to allow visualization and annotation of non-contiguous entities. This enables users to add new subspans to existing entities by selecting additional text. We integrate this new functionality with TextAE's existing editing functionality to allow easy changes to entity annotation and editing of relation annotations involving non-contiguous entities, with importing and exporting to the PubAnnotation format. Finally, we roughly quantify the problem across the entire accessible biomedical literature to highlight that there are a substantial number of non-contiguous entities that appear in lists that would be missed by most text mining systems.