• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.254-276
• /
• 2019

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, the researchers are paying much attention to Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding has shown good performance allowing words to match on a semantic level. Naively concatenating word embeddings makes common words dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the Latent Semantic Analysis input matrix. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. They are modified versions of the augment weight and the entropy frequency that combine the strength of traditional weighting schemes and word embedding. The proposed approach is evaluated on three English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization. Experimental results on the three datasets show that the proposed model achieved competitive performance compared to the state-of-the-art leading to a conclusion that it provides a better document representation and a better document summary as a result.

• Journal of Korean Library and Information Science Society
• /
• v.43 no.4
• /
• pp.403-425
• /
• 2012

This research aims to present a development plan on the Korean diaspora information resource management in a viewpoint document information and archives. This study consists of two aspects : a document investigation based on Korean diaspora and information resource and in a practical examine based on a spot of life, settlement, and movement of overseas. A lot of Korea Diaspora have immigrated to Japan, China and Russia mostly with other people in the political and economic dominant cause. They are produced a various of document information and was formed information resource management and archives in a library, a newspaper office and a publishing company. The result of this research was looked forward to help to R&D of information resource management in values and competencies for Korean diaspora.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.719-724
• /
• 2003

This paper proposed a heuristic to enhance the speed of kNN without loss of its accuracy. The proposed heuristic minimizes the computation of the similarity between two documents which is the dominant factor in kNN. To do this, the paper proposes a method to calculate the upper limit of the similarity and to sort the training documents. The proposed heuristic was implemented on the existing framework of the text categorization, so called, AI :: Categorizer and it was compared with the conventional kNN with the well-known data, Router-21578. The comparisons show that the proposed heuristic outperforms kNN about 30∼40% with respect to the execution time.

• Journal of Industrial Technology
• /
• v.21 no.A
• /
• pp.141-146
• /
• 2001

XML is fast emerging as the dominant standard to represent and exchange data in the Web. As the amount of data available in the Web has increased dramatically in recent years, the data resides in different forms ranging from semi-structured data to highly structured data in relational database. As semi-structured data will be represented by XML, XML will increase the ability of semi-structured data. In this paper, we propose an idea for extracting schema in XML document using DTD.

• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.247-256
• /
• 2009

Typical pseudo-relevance feedback methods assume the top-retrieved documents are relevant and use these pseudo-relevant documents to expand terms. The initial retrieval set can, however, contain a great deal of noise. In this paper, we present a cluster-based resampling method to select better pseudo-relevant documents based on the relevance model. The main idea is to use document clusters to find dominant documents for the initial retrieval set, and to repeatedly feed the documents to emphasize the core topics of a query. Experimental results on large-scale web TREC collections show significant improvements over the relevance model. For justification of the resampling approach, we examine relevance density of feedback documents. The resampling approach shows higher relevance density than the baseline relevance model on all collections, resulting in better retrieval accuracy in pseudo-relevance feedback. This result indicates that the proposed method is effective for pseudo-relevance feedback.

• Journal of Forest and Environmental Science
• /
• v.32 no.4
• /
• pp.367-376
• /
• 2016

Urban greenery is an important component of urban environment and is fast gaining prominence especially in the developing countries. The destruction of urban trees has resulted to the degradation of the environment, thus the introduction of green Kumasi project by Kumasi Metropolitan Assembly, Ashanti Region of Ghana. The composition and diversity of urban trees gives rise to adequate management and monitoring, thus an inventory of urban trees of the Metropolis was conducted to document complete information on its density, diversity, composition and distribution. A total tree population of 1,101 was enumerated in the principal roads of the Metropolis. The ten most encountered tree species accounted for 61.04% of all the individual tree populations with Mangifera indica being dominant. The dominant families: Fabaceae, Moraceae and Arecaceae constitute 38.57% of the tree population. Diversity of the tree species was very high. The minimum diversity criteria were met on analysis of the diversity of this population. The proportion of exotic species was high with 65.71% of the trees belonging to the introduced species. It is recommended that greater emphasis should be placed on the planting of indigenous trees in future tree planting exercise.

• Korean Institute of Interior Design Journal
• /
• v.22 no.1
• /
• pp.247-255
• /
• 2013

In this study, the colors and characteristics of Gwangbok-ro of Busan were analyzed in the standpoint of local images based on the examination of the facade designs of stores along the road of Gwangbok-ro, Busan a main street with massive population flow. To that end, the facades of stores, correlation with the city, color and locality were examined, and after the status of facade designs in Gwangbok-ro were identified through case survey by it, color images were analyzed. For color analysis, Munsell color system was used as basic tool. As a result of examining the colors in Gwangbok-ro area, the following status could be analyzed on 3 attributes of hue, brightness and chroma: First, analysis results of hue indicated that dominant color that covers 70% or more of the area represented mid brightness and low chroma in GY(36.1%) series, subsidiary color which covers 25% or more of the area mid brightness and low chroma in YR(26.5%) series, and accent color that covers less than 5% of the area high brightness and low chroma of GY(40%) series. Second, in brightness analysis, dominant color mostly represented mid brightness, subsidiary color mid brightness and accent color high brightness respectively. In particular accent color showed more intensive crowding phenomenon in high brightness. Third, as for chroma, dominant color, subsidiary color and accent color all are gathered in low chroma, however in small number of accent colors, peculiar high chroma appeared notable. In conclusion, the colors of Gwangbok-ro area analyzed based on the facade design of the stores along the road in this study were superficial colors that reflect the life of people in the area, artificial colors by improvement of the local environment. This study is meaningful in that the image of Gwangbok-ro was found through building colors in one part of the city Busan. It is judged that the study results would become useful as reference document in planning out environment colors later on.

• The korean journal of orthodontics
• /
• v.47 no.3
• /
• pp.195-206
• /
• 2017

Facial asymmetry can be classified into the rolling-dominant type (R-type), translation-dominant type (T-type), yawing-dominant type (Y-type), and atypical type (A-type) based on the distorted skeletal components that cause canting, translation, and yawing of the maxilla and/or mandible. Each facial asymmetry type represents dentoalveolar compensations in three dimensions that correspond to the main skeletal discrepancies. To obtain sufficient surgical correction, it is necessary to analyze the main skeletal discrepancies contributing to the facial asymmetry and then the skeletal-dental relationships in the maxilla and mandible separately. Particularly in cases of facial asymmetry accompanied by mandibular yawing, it is not simple to establish pre-surgical goals of tooth movement since chin deviation and posterior gonial prominence can be either aggravated or compromised according to the direction of mandibular yawing. Thus, strategic dentoalveolar decompensations targeting the real basal skeletal discrepancies should be performed during presurgical orthodontic treatment to allow for sufficient skeletal correction with stability. In this report, we document targeted decompensation of two asymmetry patients focusing on more complicated yaw-dependent types than others: Y-type and A-type. This may suggest a clinical guideline on the targeted decompensation in patient with different types of facial asymmetries.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.39-42
• /
• 2000

Extensible Markup Language(XML) is fast emerging as the dominant standard for representing data in the World Wide Web. Sophisticated query engines that allow users to effectively tap the data stored in XML documents will be crucial to exploiting the full power of XML. While there has been a great deal of activity recently proposing new semi-structured data models and query languages for this purpose, this paper explores the more conservative approach of using traditional relational database engines for processing XML documents conforming to Document Type Descriptors(DTDs). In this paper, we describe how to generate relational schemas from XML DTDs. The main issues that must be addressed inc]ode (a) dealing with the complexity of DTD element specifications (b) resolving the conflict between the two-level nature of relational schemas (table and attribute) vs. the arbitrary nesting of XML DTD schemas and (c) dealing with set-valued attributes and recursion. We now propose a set of transformations that can be used to "simplify" any arbitrary DTD without undermining the effectiveness of queries over documents conforming to that DTD.

• Journal of Korean Society for Quality Management
• /
• v.50 no.1
• /
• pp.77-89
• /
• 2022

Purpose: In order to improve the audit quality of a company, an in-depth analysis is required to categorize the audit report in the form of a text document containing the details of the external audit. This study introduces a systematic methodology to extract keywords for each group that determines the differences between groups such as 'audit plan' and 'interim audit' using audit reports collected in the form of text documents. Methods: The first step of the proposed methodology is to preprocess the document through text mining. In the second step, the documents are classified into groups using machine learning techniques and based on this, important vocabularies that have a dominant influence on the performance of classification are extracted. In the third step, the association rules for each group's documents are found. In the last step, the final keywords for each group representing the characteristics of each group are extracted by comparing the important vocabulary for classification with the important vocabulary representing the association rules of each group. Results: This study quantitatively calculates the importance value of the vocabulary used in the audit report based on machine learning rather than the qualitative research method such as the existing literature search, expert evaluation, and Delphi technique. From the case study of this study, it was found that the extracted keywords describe the characteristics of each group well. Conclusion: This study is meaningful in that it has laid the foundation for quantitatively conducting follow-up studies related to key vocabulary in each stage of auditing.