• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.570-574
• /
• 2006

KISTI portal service is currently presenting the documents with many terminologies, so users can't find the results having their intention by using an umbrella query. In this paper, we suggest user oriented retrieval service that reflects query auto-complete, related-word suggestion and query expansion that uses nouns and relationships of U-WIN which is known as a semantic language resource. We intend to advance the retrieval satisfaction of current science & technology information service by using U-WIN's semantic information and improve the service environment that user can retrieve what they want quickly and exactly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.157-160
• /
• 2006

웹 자원이 방대함에 따라, 사용자가 원하는 정보를 얼마나 정확하게 제시하느냐가 정보검색시스템 성능을 판단하는 기준이 된다. 그러나 동형이의어만을 질의어로 이용한 검색 결과는 동형이의어 각 의미에 관련된 문서가 혼재되어 있거나, 특정 의미에 관련된 문서가 집중적으로 나타나는 현상을 볼 수 있다. 이에 본 논문에서는 한국어 사용자 어휘지능망(U-WIN)의 관계정보를 이용하여 질의어의 모호성을 해결하고 의미적 정보검색의 기반을 마련하고자 한다. 우선, 전문분야에 주로 사용되는 동형이의어와 보편적으로 사용하는 동형의어를 구번하여 질의어로 선정하고, '질의어+상위어' 형태의 확장 질의어에 대해 두 개의 포탈사이트(Google, Naver)를 대상으로 웹 문서를 검색하여 정확률이 각각 81.5%(Naver), 65.5%(Google)로 나타났다.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.189-193
• /
• 2007

In this paper, we designed a methodology to expand the WordNet. We added unknown terms like IT technical terms to the existing WordNet by using web search. The WordNet is an online taxonomy representing the relationships among terms, but it usually showed limitation to contain new technical terminologies. That's why we tried to expand the WordNet. Firstly, when we met unregistered terms in WordNet, we built a query of those terms for web search. Given a web search results, we tried to find out terms with a high-level relatedness with the unregistered terms. We used the Korean Morphological Analyzer to score the relatedness between terms and located the unregistered term as a hyponym of terms with high score of relatedness.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.207-218
• /
• 2020

Recently, due to the increase of online reviews and the development of analysis technology, the interest and demand for online review analysis continues to increase. However, previous studies have not considered the emotions contained in each vocabulary may differ from one reviewer to another. Therefore, this study first classifies the customer group according to the customer's grade, and presents the result of analyzing the difference by performing review analysis for each customer group. We found that the price factor had a significant influence on the evaluation of products for customers with high ratings. On the contrary, in the case of low-grade customers, the degree of correspondence between the contents introduced in the mall and the actual product significantly influenced the evaluation of the product. We expect that the proposed methodology can be effectively used to establish differentiated marketing strategies by identifying factors that affect product evaluation by customer group.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.55-65
• /
• 2022

As Internet and mobile technology is developing, the educational environment is changing from the traditional passive way into an active one driven by learners. It is important to construct the proper learner's profile for personalized education where learners are able to study according to their learning levels. The existing studies on ICT-based personalized education have mostly focused on vocabulary and learning contents. In this paper, learning profile is constructed with not only vocabulary but grammar to define a learner's learning status in more detailed way. A proficiency metric is defined which shows how a learner is accustomed to the learning contents. The simulational results present the suggested approach is effective to the evaluation essay data with each learner's proficiency that is determined after pre-learning process. Additionally, the proposed analysis technique enables to provide statistics or graphs of the learner's status and necessary data for the learner's learning contents.

• Journal of Hospice and Palliative Care
• /
• v.6 no.1
• /
• pp.11-21
• /
• 2003

This paper addresses the minor differences in the description of pain in Korean language in order to develop a standarized cancer pain aneument tool for Korean adults, Korean Cancer Pain Assessement Tool. The subtle differences in the meaning of expressions used cannot be translated into English and therefore we omiltted the English abstract.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.151-157
• /
• 2008

This study aims to construct the aged portal sites based on multimedia DB on the basis of request for systematic collection and management of the aged-related specific information which are spreading and construct Multimedia Information System for the Aged by developing digital contents to offer the aged-related information. It also tries to construct ontology based information repository for the aged that includes on/off-line. It extracts semantic relationship of each information by analysing the aged information, knows the hierarchical structure of each vocabulary, and designs and constructs an ontology based repository by designing function of each agent through that. It has also developed a variety of information and digital contents, constructed a systematic multimedia DB for the aged welfare homes, developed web framework which makes automatic registration of the aged welfare homes possible, and designed in order to support the use state of enterprises/homes and statistics state.

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.21-27
• /
• 2005

본 논문에서는 국가에서 추진하는 차세대신성장동력산업과 관련된 특정 분야('바이오 신약/장기' 분야 중 '면역 기능 제어')를 선택하여, 기구축된 면역학 전문용어사전을 비롯하여 의학용어사전, 표준국어대사전 등을 참조하여 핵심 용어와 관련 용어를 중심으로 면역학 시소러스(어휘 3,462개) 및 온톨로지(개념 노드 4,703개)를 구축하였다. 이것은 전문용어사전부터 온톨로지에 이르기까지 통일화된 표준 체계를 가지고 있으며, 도메인 온톨로지를 구축하여 향후 온톨로지 개발 방향을 설정할 수 있는 계기가 되었다고 할 수 있다. 또한 면역학 시소러스는 검색의 성능을 향상시킬 수 있도록 충분한 양의 데이터를 구축하였고 면역학 온톨로지는 언어처리적 관점에서의 온톨로지를 표현하였다. 이는 정보검색에서의 효율성을 비롯하여, 특정 웹 온톨로지 언어를 이용한 웹 온톨로지로의 변환성, 대규모 도메인 온톨로지라는 점에서 의미를 가진다고 할 수 있다.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.585-592
• /
• 2017

As development of personal devices have made everyday use of internet much easier than before, it is getting generalized to find information and share it through the social media. In particular, communities specialized in each field have become so powerful that they can significantly influence our society. Finally, businesses and governments pay attentions to reflecting their opinions in their strategies. The stock market fluctuates with various factors of society. In order to consider social trends, many studies have tried making use of bigdata analysis on stock market researches as well as traditional approaches using buzz amount. In the example at the top, the studies using text data such as newspaper articles are being published. In this paper, we analyzed the post of 'Paxnet', a securities specialists' site, to supplement the limitation of the news. Based on this, we help researchers analyze the sentiment of investors by generating a domain-specific sentiment lexicon for the stock market.