• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.9-13
• /
• 2020

관계 추출은 주어진 문장이나 문서에 존재하는 개체들 간의 의미적 관계를 찾아내는 작업을 말한다. 최근 문서 수준 관계 추출 말뭉치인 DocRED가 공개되면서 문서 수준 관계 추출에 대한 연구가 활발히 진행되고 있다. 또한 사전 학습된 Masked Language Model(MLM)이 자연어처리 분야 전체에 영향력을 보이면서 관계 추출에서도 MLM을 사용하는 연구가 진행되고 있다. 그러나 문서 수준의 관계 추출은 문서의 단위가 길기 때문에 Self-attention을 기반으로 하는 MLM을 사용하면 모델의 계산량이 증가하는 문제가 있다. 본 논문은 이 점을 보완하기 위해 관계 추출에 필요한 문장을 선별하는 간단한 전처리 방법을 제안한다. 또한 문서의 길이에 상관없이 관계 추출에 필요한 어휘 정보를 자동으로 습득 할 수 있는 Relation-Context Co-attention 방법을 제안한다. 제안 모델은 DocRED 말뭉치에서 Dev F1 62.01%, Test F1 59.90%로 높은 성능을 보였다.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.2
• /
• pp.1-22
• /
• 2023

In this study, we propose a plan to reflect LRM in various library-related standards or systems through analyzing the reflection of LRM in RDA. To this end, LRM and RDA 2020 were analyzed in terms of entities, relationships, attributes, and encoding schemes. First of all, for the mapping of entities, relationships, and attributes, all properties and relationships were extracted for each entity of RDA, LRM elements corresponding to each property and relationship were found and mapped, and encoding schemes were additionally compared. As a result, the things to consider in the standards and systems to which LRM is to be applied are: first, entities development considering the LRM hierarchy; second, new relation or shortcut path relation development; third, attributes expansion according to the entities considering the LRM hierarchical structure, and fourth, the development of various encoding scheme. Through this study, it will be possible to find an application plan using the application of RDA as a model in standards or systems to accept LRM.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.379-384
• /
• 2022

관계 추출은 두 개체 간의 관계를 식별하는 작업이며, 비정형 텍스트를 구조화시키는 역할을 하는 작업 중 하나이다. 현재 관계 추출에서 다양한 모델에 대한 연구들이 진행되고 있지만, 한국어 관계 추출 모델에 대한 연구는 영어에 비해 부족하다. 따라서 본 논문에서는 NE(Named Entity)태그 정보가 반영된 TEM(Typed Entity Marker)과 의존 구문 그래프를 이용한 한국어 관계 추출 모델을 제안한다. 모델의 학습과 평가 말뭉치는 KLUE에서 제공하는 관계 추출 학습 말뭉치를 사용하였다. 실험 결과 제안 모델이 68.57%의 F1 점수로 실험 모델 중 가장 높은 성능을 보여 NE태그와 구문 정보가 관계 추출 성능을 향상시킬 수 있음을 보였다.

• Korean Institute of Interior Design Journal
• /
• no.31
• /
• pp.71-78
• /
• 2002

Understanding the consumer changed life styles are integrated, mutual complement for user's worth and consciousness, the life of consumption, etc. Recently, Apartment Model House has built for distribute to Apartment house When they enter the units after 2 or 3 years. So, Interior designer make an inference from the changed life styles. But, We don't have enough information to trace the design trend about residential space design. Design database is correspond with interior space and structured entity relationship. There are three parts in this Database, Type, Elements and Relation information. Type are composed size, ages, style, and space, Elements are materials and space elements. Relation information are publishing, designer, exhibition, construction company, remodeling, Intoner design and User favorite styles are the development in web environment. This research supplies interior design information for Web environment and trend analysis supports collaboration with development of interior design information database.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.577-580
• /
• 2003

The purpose of this study was to make a database model for financial feasibility study of buildings offered for sale which is helpful for improvement of business ability in construction and confidence of a project from a related participant. At first, we studied several thesis and met some professionalist which work for construction and did a first survey for examining latest situation of a feasibility study in construction. As a result, even though feasibility study is important, factors for information management wasn't systemized. So we did a second survey for fixing Factors of the database model. The database model was composed of the factors that we got from the second survey. ER(Entity-Relationship) analysis was used to making it. We expect thar we can get more reasonable information to study financial feasibility study and can diminish risks of project through the database model. So the result of this study was to make a database model for more reasonable financial feasibility study of building offered for sale.

• Journal of the Korean Society for Library and Information Science
• /
• v.38 no.3
• /
• pp.5-21
• /
• 2004

FRBR, as is new conceptual model of bibliography based on entity-relation model, direct to revision of AACR. OCLC and other bibliographic utility develop algorithm that cluster relative bibliographic records automatically, which were derived from one original work, and web-based prototype for FRBR browsing. But the state of domestic research level stay at conceptual reconsideration of FRBR model.7his study focused on analyzing FRBR algorithm and application of KORMARC database.

• Journal of Korean Library and Information Science Society
• /
• v.45 no.4
• /
• pp.365-390
• /
• 2014

This study intend to find the application methods of the FRBR model about legislation by analyzing a law life cycle from the enactment to the amendment and abolition of legislation and the type of the change after abolition. The legislation is the work as an aggregate entity consisting legal provisions and each provision is also the work. They are in the Whole-to-Part relation. The legislation has a effect by being published in the official gazette, and the updated text or the translated text is not the official version. Even if the name of the legislation is changed, it is treated as the same entity when it is not abolished and the simple rectifying text expressed in the official gazette is also legally valid. The Libraries Act has been replaced by the Libraries Act(old version), the Libraries Promotion Act, the Libraries and Reading Promotion Act and the Libraries Act(new version) in the order named, and it can be bounded into a superwork. For these examples, we provided the application method of FRBR model and suggested the actual application cases regarding Work, Expression, Manifestation and Item which are in Group 1 of FRBR model for the Libraries Act.

• Anxiety and mood
• /
• v.1 no.1
• /
• pp.14-17
• /
• 2005

By the influence of the descriptive approach of DSM-III, the anxiety became the same thing as the anxiety disorder to the clinicians. This unfortunate result sacrificed psychodynamic model of symptom formations and simplified the anxiety as one of the disease entity not as the overdetermined symptoms. These phenomenon awakened the psychoanalytic interest which was in sleep. Freud was the first major articulator of the basic significance of anxiety in human behavior. He attributed the particular quality of the anxiety experience to the trauma of birth, and subsequently to the fear of castration. Such classification of the anxiety according to the psychosexual development is helpful for the clinicians in understanding the origin of anxiety which the patient shows during the psychotherapy. The other analytical view of interpersonal psychoanalysis came from Sullivan. A large part of his therapy is taken up with recognizing and correcting parataxic distortions that interfere with realistic self-appraisal of events and of oneself in relation to others. Perhaps no explanation is the 'most basic' explanation for human anxiety. Anxiety is a multifaceted entity consisting of aspects of realm of discourse. Existential anxiety is inescapable in Western culture but it can be transcended by the cultivation of mind in Eastern culture. The analysts need to stay attuned to their own propensities for anxiety and must permit their own experiences with anxiety to be the grist for the psychotherapeutic mill.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.1 no.1
• /
• pp.49-53
• /
• 1978

Yet objective of this paper to spell out in detail the relationship between factors design techniques of data analysis and the design of simulation model of the management organization. Yet an organization is more than a collection of individuals. It is something more than the sum of its Parts: it exists as an entity with its own definable objectives. The management process comprise those activities or functions that managers must perform to effectively carry out this asizned role. However, now that O.R. and system approach has been generalized and the assembly system of hard ware or soft ware through computerization is being improved, the systematization of scientific organization is urgently needed. This paper is to set forth :he problem and solution which are most fit for the management organization in relation to computer. Procedure developed are : 1. Interpretation of the management organization. 2. Design of the computer simulation. 3. Application.

• Spatial Information Research
• /
• v.14 no.2 s.37
• /
• pp.245-260
• /
• 2006

A practical use of the location information and user requirement are increased in a mobile environment which supports the portability. And Various service which GIS is related with a Spatial DB have been processed. Generally, logical relation of a traffic network which organizes the Road DB uses a basic node-link structure. In this way, Designed structure can not be flexible at various model apply and are not efficient with a database retrieval in a maintenance management side. In this research, We supplement with the problem of a existing network model and the limitation of the building through the design of a network model which uses dynamic segmentation. And we tried to implement efficient hierarchy model at the retrieval of the network and presentation. Designed model supports a stage presentation of various level and a hierarchy entity relation and We are expected to supplement a network spatial modelling function which the GIS has.