• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.451-464
• /
• 2016

Nowadays, entity search such as Google Product Search and Yahoo Pipes has been in the spotlight. The entity search engines have been used to retrieve web pages relevant with a particular entity. However, if an entity (e.g., Chinatown movie) has various meanings (e.g., Chinatown movies, Chinatown restaurants, and Incheon Chinatown), then the accuracy of the search result will be decreased significantly. To address this problem, in this article, we propose a novel method that quantifies the importance of search queries and then offers the best query for the entity search, based on Frequent Pattern (FP)-Tree, considering the correlation between the entity relevance and the frequency of web pages. According to the experimental results presented in this paper, the proposed method (59% in the average precision) improved the accuracy five times, compared to the traditional query terms (less than 10% in the average precision).

• Journal of KIISE:Software and Applications
• /
• v.35 no.7
• /
• pp.405-416
• /
• 2008

To overcome the limitation of keyword-based integrated search, this study shows entity-centric integrated search method using URI scheme. Our system generates entity pages in ways of analyzing user's keyword and instances matched with it, selecting optimal entity type, and calling unit services simultaneously. Topic information extracted from articles is propagated to persons, institutions, and locations by reasoning for providing topic-centric information. With comparative experiments based on search results and usability tests, we proved that this approach is superior to keyword-based integrated search served by CiteSeer and Google Scholar.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.253-256
• /
• 2009

This paper describes a vertical search system based on multiple entity-centric unification, which enables to deal with the search queries including multiple domains. To implement the system, we introduced two search technologies; one is for merging service components dynamically according to the entities in the search keywords, and the other is for searching fields with appropriate entities. Our current system includes about 453,000 overseas journal papers for article information search and two entity types; research topic and researcher.

• Interdisciplinary Bio Central
• /
• v.3 no.3
• /
• pp.9.1-9.5
• /
• 2011

Entity Attribute Value (EAV) is the widely used solution to represent high dimensional and sparse data, but EAV is not search efficient for knowledge extraction. In this paper, we have proposed a search efficient data model: Optimized Entity Attribute Value (OEAV) for physical representation of high dimensional and sparse data as an alternative of widely used EAV. We have implemented both EAV and OEAV models in a data warehousing en-vironment and performed different relational and warehouse queries on both the models. The experimental results show that OEAV is dramatically search efficient and occupy less storage space compared to EAV.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.349-357
• /
• 2007

Named entities (NEs) are important in many Natural Language Processing (NLP) applications, and discovering NE-related relations in texts may be beneficial for these applications. This paper proposes a method to extract the ISA relation between a "named entity" and its category, and an IS-RELATED-TO relation between the category and its related object. Based on the pattern extraction algorithm "Person Category Extraction" (PCE), we extend it for solving our problem. Our experiments on Wall Street Journal (WSJ) corpus show promising results. We also demonstrate a possible application of these relations by utilizing them for semantic search.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.851-867
• /
• 1999

Numerous proposals for extending the relational data model as well as conceptual and object-oriented data models have been suggested. However, there has been relatively less research in the area of defining segmented storage structure and data migration strategies for temporal data. This paper presents the segmented storage structure in order to increment search performance and the two data migration strategies for segmented storage structure. this paper presents the two data migration strategies : the migration strategy by Time granularity, the migration strategy by LST-GET. In the migration strategy by Time Granularity, the dividing time point to assign the entity versions to the past segment, the current segment, and future segment is defined and the searching and moving process for data validity at a granularity level are described. In the migration strategy by LST-GET, we describe the process how to compute the value of dividing criterion. searching and moving processes are described for migration on the future segment and the current segment and entity versions 새 assign on each segment are defined. We simulate the search performance of the segmented storage structure in order to compare it with conventional storage structure in relational database system. And extensive simulation studies are performed in order to compare the search performance of the migration strategies with the segmented storage structure.

• Journal of National Security and Military Science
• /
• s.1
• /
• pp.269-310
• /
• 2003

AS Extensible Markup Language(XML) is emerging as the data format of the Internet era, there are increasing needs to efficiently transform between database and XML documents. In this paper, we propose a schema transformation method from relational database to XML database. To transform the schema, we represent input schema as Entity-Relationship diagram. Entity-Relationship model translator scans the input Entity-Relationship diagram using BFS (breadth First Search) and translates the diagram into hierarchical structure model. The XML Schema generator produces XML Scema code using the transformed hierarchical structure model. The proposed method has a merit that having reusability facility of XML Schema property in comparison with existing researches.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.90-95
• /
• 2016

개체명 연결이란 문장 내 어떤 단어를 특정 사물이나 사람, 장소, 개념 등으로 연결하는 작업이다. 과거에는 주로 연결 대상 단어 주변 문맥에서 자질 공학을 거쳐 입력을 만들고, 이를 이용해 SVM이나 Logistic Regression 혹은 유사도 계산, 그래프 기반 방법론 등으로 지도/비지도 학습하여 문제를 풀어왔다. 보통 개체명 연결 문제의 출력 부류(class)가 사물이나 사람 수만큼이나 매우 커서, 자질 희소성 문제를 겪을 수 있다. 본 논문에서는 이 문제에 구조적으로 더 적합하며 모형화 능력이 더 뛰어나다 여겨지는 딥러닝 기법을 적용하고자 한다. 다양한 딥러닝 모형을 이용한 실험 결과 LSTM과 Attention기법을 같이 사용했을 때 가장 좋은 품질을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.90-95
• /
• 2016

개체명 연결이란 문장 내 어떤 단어를 특정 사물이나 사람, 장소, 개념 등으로 연결하는 작업이다. 과거에는 주로 연결 대상 단어 주변 문맥에서 자질 공학을 거쳐 입력을 만들고, 이를 이용해 SVM이나 Logistic Regression 혹은 유사도 계산, 그래프 기반 방법론 등으로 지도/비지도 학습하여 문제를 풀어왔다. 보통 개체명 연결 문제의 출력 부류(class)가 사물이나 사람 수만큼이나 매우 커서, 자질 희소성 문제를 겪을 수 있다. 본 논문에서는 이 문제에 구조적으로 더 적합하며 모형화 능력이 더 뛰어나다 여겨지는 딥러닝 기법을 적용하고자 한다. 다양한 딥러닝 모형을 이용한 실험 결과 LSTM과 Attention기법을 같이 사용했을 때 가장 좋은 품질을 보였다.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.367-374
• /
• 2010

The technology of wireless internet has been recently developing very fast and affecting everyday life using mobile media. In this paper, we propose an algorithm that can get necessary information such as image pixels from photos taken by mobile phones and search approximate values from reference database in the internet. This algorithm is expected to enable us to use a mobile phone to take a picture of something we see in every day life and go online to search for some information on that entity in the internet. An example system employing this proposed algorithm is illustrated in this paper.