• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.457-461
• /
• 2001

본 논문은 동사의 의미표상과 명사의 한정성의 강호관계를 중심으로 목적어의 생략현상을 검토하였다. 한국어는 영어 같은 언어와 달리 주어, 목적어 등이 자주 생략된다. 이 연구는 한국어의 목적어 생략이 단순히 인간성 (humanness), 주체성 (agency), 한정성(definiteness) 등 명사의 의미자질에 의해서만 결정되는 것이 아니라, 다음 두 가지 제약이 결정적으로 작용함을 제안하고자 한다. 첫째, 목적어 생략은 행동양상 (mold of agent act)과 원인 (cause)을 심층적으로 포함하는 소위 '핵심 타동사 (core transitive)'와 선행사의 한정성 정도에 의해 결정되는데, 구체적으로 목적어 생략은 한정성 자질을 가진 선행사가 없는 담화에서는 허용되지 않는다는 제약이다. 둘째, 타동사와 명사의 한정성과는 독립적으로, 한국어의 목적어 생략은 또한, 추론에 의거하여 보다 더 적절히 해석될 수 있는 경우를 실증적으로 보이고자 한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2008.11a
• /
• pp.349-352
• /
• 2008

본 논문에서는 시맨틱 웹 기반의 학술 정보 분석 서비스 프레임워크인 OntoFrame에 대해 소개하고자 한다. 2005년부터 개발되기 시작한 OntoFrame은 매년 새로운 서비스와 기술로 확장되고 있으며 OntoFrame2008에서는 다중 키워드 기반의 검색 서비스 및 다중 개체 중심적 통합 검색기능을 제공한다. 본 서비스는 키워드의 개체를 판단한 후에 인력, 주제, 인력+주제에 해당하는 서비스 API를 호출하여 추론 서비스 페이지를 구성한다. 이때 시스템에서 자동으로 판단되는 개체의 모호함을 제거하기 위해서 사용자의 의도라고 판단되는 최적의 개체 조합 페이지뿐만 아니라 해당 키워드에서 나타날 수 있는 모든 개체 조합의 후보 페이지들을 제공해주어 시스템의 일방적인 추천 서비스의 단점을 없앴다. 그리고 서비스의 결과로 제공되는 페이지에서 링크를 통한 추가조건 검색도 제공해 주어 사용자의 검색 의도를 정확하게 파악하여 편리한 정보 획득을 도와주는 시스템으로 개발하고 있다. OntoFrame2008은 여러 가지 풍부한 분석 서비스를 제공하여 연구자들이 학술 정보 검색 과정에 많은 도움이 되는 추론 서비스를 제공하고 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.157-159
• /
• 2004

시맨틱 웹 기술을 활용한 시맨틱 검색은 문서의 의미를 온톨로지의 메타데이터로 생성하여 이를 바탕으로 검색을 수행하게 된다. 이와같은 온톨로지 기반의 시맨틱 검색은 논리를 바탕으로 추론을 적용할 수 있다. 본 논문에서는 온톨로지 기반의 추론을 적용한 시맨틱 검색 시스템을 언급하고 시맨틱 검색 시스템에서의 성능향상을 위해 추론엔진의 작업메모리 영역의 부하를 줄여 기존의 시스템보다 빠른 성능의 시맨틱 검색 시스템을 제안한다. 본 논문에서 시맨틱 검색 시스템의 성능향상을 위한 방법론으로는 다음과 같다 첫째, 추론엔진이 검색 도메인내의 전체 메타데이터를 가지고 추론을 수행하지 않고 메타데이터의 온톨로지부분 만을 사용하여 사용자가 원하는 질의문을 추론하여 검색에 사용하게 한다. 둘째, 시맨틱 검색 방법에서 Dirtectly 매칭 검색과 시맨틱 추론검색을 병행하여 수행하게 한다. 이를 위해 본 논문에서는 메타데이터의 온톨로지부분과 인스턴스부분을 분리하는 단계와 분리된 온톨로지부분에서 사용자가 원하는 질의를 추론하는 단계, 추론된 질의문을 검색시스템에서 매칭하는 단계를 수행하게 된다. 이러한 방법은 메타데이터의 양이 증가하여도 온톨로지부분은 증가하지 않으므로 추론엔진에서 전 방향 추론단계의 수행시간을 단축과 추론엔진의 호출 횟수를 단축시키는 결과를 가져온다.

• Language and Information
• /
• v.8 no.1
• /
• pp.1-26
• /
• 2004

This paper investigates the nature of the discourse domain involved with focus sentences. The major theories of focus including Roothian Alternative Semantics are critically reviewed: Alternative Semantics takes a contradictory attitude toward the truth conditional aspect of free focus. The truth conditional differences are treated as a pragmatic inference, while they are captured by the semantic mechanism, that is, the alternative sets generated by focus constructions. In addition, the alternative sets are ad hoc since they are generated only for focus constructions. This paper attempts to show that the alternative sets introduced by foci in the framework of Alternative Semantics are neither necessary nor sufficient for an analysis of focus. It is argued that the domain sets simply provided by the model itself suffices for a proper analysis of focus constructions.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.2
• /
• pp.49-63
• /
• 2008

RDF is the base ontology model which is used in Semantic Web defined by W3C. OWL expands the RDF base model by providing various vocabularies for defining much more ontology relationships. Recently Jain and Farkas have suggested an RDF access control model based on RDF triple. Their research point is to introduce an authorization conflict problem by RDF inference which must be considered in RDF ontology data. Due to the problem, we cannot adopt XML access control model for RDF, although RDF is represented by XML. However, Jain and Farkas did not define the authorization propagation over the RDF upper/lower ontology concepts when an RDF authorization is specified. The reason why the authorization specification should be defined clearly is that finally, the authorizatin conflict is the problem between the authorization propagation in specifying an authorization and the authorization propagation in inferencing authorizations. In this article, first we define an RDF access authorization specification based on RDF triple in detail. Next, based on the definition, we analyze the authoriztion conflict problem by RDF inference in detail. Next, we briefly introduce a method which can quickly find an authorization conflict by using graph labeling techniques. This method is especially related with the subsumption relationship based inference. Finally, we present a comparison analysis with Jain and Farkas' study, and some experimental results showing the efficiency of the suggested conflict detection method.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.113-125
• /
• 2018

Recently, with the advent of the Big Data era, we have gained the capability of acquiring vast amounts of knowledge from various fields. The collected knowledge is expressed by well-formed formula and in particular, OWL, a standard language of ontology, is a typical form of well-formed formula. The symbolic reasoning is actively being studied using large amounts of ontology data for extracting intrinsic information. However, most studies of this reasoning support the restricted rule expression based on Description Logic and they have limited applicability to the real world. Moreover, knowledge management for inaccurate information is required, since knowledge inferred from the wrong information will also generate more incorrect information based on the dependencies between the inference rules. Therefore, this paper suggests that the SWAT, knowledge management system should be combined with the SWRL (Semantic Web Rule Language) reasoning based on ATMS (Assumption-based Truth Maintenance System). Moreover, this system was constructed by combining with SWRL reasoning and ATMS for managing large ontology data based on the distributed In-memory framework. Based on this, the ATMS monitoring system allows users to easily detect and correct wrong knowledge. We used the LUBM (Lehigh University Benchmark) dataset for evaluating the suggested method which is managing the knowledge through the retraction of the wrong SWRL inference data on large data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.37-45
• /
• 2013

In this paper proposes the latest network-assisted online telemedicine service to coincide with the point being discussed for health care providers to match patients, patients with personalized medical service support system. In order to design the system, to understand the requirements of the patient personalized medical support service system, the data were normalized and were designed architecture client server structure. Further, in order to implement the system that was designed to define the structure of server and client, ontology repository, we implement the system. In this paper, as a result of the test by creating a scenario and prerequisites for testing patient personalized medical service support system that is design and implementation, selecting a patient's condition, department of symptoms by the selected but it was confirmed that the inference is, inference medical institutions that fits department inferred one following upon the items medical patient has the required.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.963-973
• /
• 2016

Providing a semantic knowledge system using media ontologies requires not only conventional axiom reasoning but also knowledge extension based on various types of reasoning. In particular, spatio-temporal information can be used in a variety of artificial intelligence applications and the importance of spatio-temporal reasoning and expression is continuously increasing. In this paper, we append the LOD data related to the public address system to large-scale media ontologies in order to utilize spatial inference in reasoning. We propose an RDFS/Spatial inference system by utilizing distributed memory-based framework for reasoning about large-scale ontologies annotated with spatial information. In addition, we describe a distributed spatio-temporal SPARQL parallel query processing method designed for large scale ontology data annotated with spatio-temporal information. In order to evaluate the performance of our system, we conducted experiments using LUBM and BSBM data sets for ontology reasoning and query processing benchmark.