• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.12
• /
• pp.577-584
• /
• 2015

In general, Q&A system retrieves passages by matching terms of a question in order to find an answer to the question. However it is difficult for Q&A system to find a correct answer because too many passages are retrieved and matching using terms is not enough to rank them according to their relevancy to a question. To alleviate this problem, we introduce a topic for a sentence, and adopt it for ranking in Q&A system. We define a set of person-related topic class and a clue expression which can indicate a topic of a sentence. A topic classification system proposed in this paper can determine a target topic for an input sentence by using clue expressions, which are manually collected from a corpus. We explain an architecture of the topic classification system and evaluate the performance of the components of this system.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.585-592
• /
• 2016

A topic segmentation module is to divide statements or conversations into certain topic units. Until now, topic segmentation has progressed in the direction of finding an optimized set of segments for a whole document, considering it all together. However, some applications need topic segmentation for a part of document which is not finished yet. In this paper, we propose a model to perform topic segmentation during the progress of the statement with a supervised learning model that uses a convolution neural network. In order to show the effectiveness of our model, we perform experiments of topic segmentation both on-line status and off-line status using C99 algorithm. We can see that our model achieves 17.8 and 11.95 of Pk score, respectively.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.178-186
• /
• 2018

Subject classification of thesis units is essential to serve scholarly information deliverables. However, to date, there is a journal-based topic classification, and there are not many article-level subject classification services. In the case of academic papers among domestic works, subject classification can be a more important information because it can cover a larger area of service and can provide service by setting a range. However, the problem of classifying themes by field requires the hands of experts in various fields, and various methods of verification are needed to increase accuracy. In this paper, we try to classify topics using the unsupervised learning algorithm to find the correct answer in the unknown state and compare the results of the subject classification algorithms using the coherence and perplexity. The unsupervised learning algorithms are a well-known Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA) and Latent Semantic Indexing (LSI) algorithm.

• Journal of Korean Library and Information Science Society
• /
• v.48 no.4
• /
• pp.21-47
• /
• 2017

This study aims to analyze features of topics about AI(Artificial Intelligence) which is gaining a massive attention these days. Newspaper articles published from 2016 to June, 2017 were selected to analyze key subjects. The reason why the period was selected is people started to get attention on AI since 2016 as AlphaGo came out and gave a shock. The number of coded main message was 1,210 in 525 newspaper articles in total. The messages were categorized as three subject categories: the seven major categories, 62 middle categories. and minor categories. The seven major categories contains issues such as AI research, AI application, AI business, AI era, AI argument, AlphaGo, and other topics. The first features of issues about AI found in the major subject categories is that they are various and complicate. Second, it is important that social and policy-level issues related AI, such as job losses, misuse, and error should be dealt with to utilize AI safely. Last, issues related the role of human and revolution of education system in the AI era were shown as subjects which are important but hard to discuss.

• Journal of Korean Library and Information Science Society
• /
• v.41 no.2
• /
• pp.147-169
• /
• 2010

The purpose of this study is to analyze the historical process and characteristics of subject headings related to Korea, China, Japan in the LCSH, from the first edition to 31th ed. The analytic results show that the headings in the 31th edition include in Korea 713, China 1,742, Japan 2,647, compared to Korea headings 4, China headings 49, Japan headings 24 in the first edition. Some subject headings considered important and essential are left out. We can also recognize the some headings are relatively too subdivided. The omitted and insufficient Korean, Chinese, Japanese subject headings are considered to be tied up with library policies of LC. Therefore our active support such as donation are being called for collecting more detailed analysis of Korea, China, Japan-related publications in LC.

• Journal of Korea Technology Innovation Society
• /
• v.15 no.2
• /
• pp.369-399
• /
• 2012

Purpose: Health technology research & development is an important area to leading future. This study examined the current trends for 'oncogene' based on the research subject network to deduce a research front. Method: Papers were extracted from PubMed database using MeSH term for studies on 'oncogenes' and further categorized as papers published by Korean. Keywords were collected from all of articles. Research subject network was generated by keywords. Research subject network was analyzed by weighted degree centrality based social network analysis and transition of research subjects was analyzed by the time series. Results: On 'oncogenes', 'Genes, ras', 'Apoptosis', 'Signal Transduction' had a high degree centrality and currently 'Antineoplastic Agents', 'Prognosis', and 'Tumor Markers, Biological' were widely conducted. Conclusion: Consistency of research trend pattern was found by analyzing oncogene network with compromised to international vs. domestic trends. Analyzing keyword networks in various subject area, those will allow us to predict the research progress and propose evidence of research & developmental strategy.

• Journal of the Korean Society for Library and Information Science
• /
• v.52 no.1
• /
• pp.381-400
• /
• 2018

The purpose of this study is to analyze the currently operating subject guides in academic libraries and to suggest measures for improvements of them. To do this, 22 out of 151 academic libraries which have more than 1,000 enrolled college students in the university and two institutes of science and technology were selected and the libraries were analyzed according to 12 criteria. The main results of the data analysis were as follows: First, the subject guides did not clearly indicate which service tool to use. Second, there was a difference in the subject guide format in the same academic library. Third, libraries tried to provide a lot of information sources on the subject guides without considering users' needs. By offering many kinds of information sources, students had to choose the information sources they needed. Improvement plans are: First, it is necessary to develop the subject guide of the college courses. Second, Content-based subject guides are necessary through standardized format. Third, it is necessary to unify the name of menu of information resource. Fourth, the number of information sources included in the subject guides should be minimized. Fifth, it is necessary to establish a cooperation system between academic libraries to develop the subject guides.

• Journal of Internet Computing and Services
• /
• v.7 no.2
• /
• pp.71-80
• /
• 2006

In web search engines, there are two main methods: directory searching and keyword searching. Keyword searching shows high recall rate but tends to come up with too many search results to find which users want to see the pages. Directory searching has also a difficulty to find the pages that users want in case of selecting improper category without knowing the exact category, that is, it shows high precision rates but low recall rates. We designed and implemented a new web search engine to resolve the problems of directory search method. It regards a category as a fuzzy set which contains keywords and calculate the degree of inclusion between categories. The merit of this method is to enhance the recall rate of directory searching by expanding subcategories on the basis of similarity.

• Journal of the Korean Society for Library and Information Science
• /
• v.49 no.4
• /
• pp.179-201
• /
• 2015

The subject heading is an elaborate access tool for subject browsing and searching in information retrieval environment. The purpose of this study is to suggest the applicable facets to subject headings in Korea. First, the concepts of subject and the definitions of facets were investigated in the literature review. Second, six cases including OCLC's FAST, PRECIS, "Thesaurus construction and use", CC $7^{th}$ edition, BC $2^{nd}$ Edition, and UDC $3^{rd}$ Edition were analyzed to focus on configuration of facets as case studies. Based on the results, twenty-two facets were proposed including Topical, Event, Geography, Chronology, Personal and Corporate Name, Title, Form, Genre, Language, and Person facets as 11 top facets. Also, Topical-Thing/Entity and Topical-Action/Status, Part, Kind, Property, Whole, Material, Patient, Product, By-Product and Agent facets as sub-facets of Topical facet.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.2
• /
• pp.95-102
• /
• 2005

Currently, the government has been established GIS DB related to river as a part of the river map digitization projects such as RIMGIS and flood map. This study was aimed to demonstrate the generation of thematic maps related to river space and their management system, the one of the major river thematic maps proposed from the precedent study "Establishment of River Thematic Map Project" in an effort to maximize the utilization of river related database, the major product of the project for digitization of river maps. This study includes amending database model for building river thematic maps. Also, metadata were amended and built for efficient management and distribution of the river related data based on the national standard metadata proposed from "Establishing Standard Metadata" sponsored by National Geography Institute in 2003 for more effective management of river thematic maps. In addition, this study analyzed the method for utilizing existing data from RIMGIS and WAMIS as well as digital topographic maps to produce 25 river thematic maps in accordance of defined building procedure. Management system of the river thematic maps for Kyungan watershed has been generated for effective managing river thematic maps based on the design and pilot generation of river thematic maps, and metadata management function has been added into the management system.