• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.63-76
• /
• 2012

We propose a Korean compound noun semantic tagging system using statistical compound noun decomposition and semantic relation information extracted from a lexical semantic network(U-WIN) and dictionary definitions. The system consists of three phases including compound noun decomposition, semantic constraint, and semantic tagging. In compound noun decomposition, best candidates are selected using noun location frequencies extracted from a Sejong corpus, and re-decomposes noun for semantic constraint and restores foreign nouns. The semantic constraints phase finds possible semantic combinations by using origin information in dictionary and Naive Bayes Classifier, in order to decrease the computation time and increase the accuracy of semantic tagging. The semantic tagging phase calculates the semantic similarity between decomposed nouns and decides the semantic tags. We have constructed 40,717 experimental compound nouns data set from Standard Korean Language Dictionary, which consists of more than 3 characters and is semantically tagged. From the experiments, the accuracy of compound noun decomposition is 99.26%, and the accuracy of semantic tagging is 95.38% respectively.

• Science of Emotion and Sensibility
• /
• v.7 no.2
• /
• pp.123-131
• /
• 2004

This study has an aim to find out sensible factors of hahae Mask and to be helpful in developing design of products related with cultural products. This study selected and analyzed 32 vocabularies about sensible adjective to evaluate image of hahae Mask. Firstly, this study investigated image of hahae Mask through 32 vocabularies about sensible adjective and categorized 5 factors including 'attractive', 'native', 'interesting', 'active', and 'elaborate'. Secondly, sense had significant differences in 'native' and, 'interesting' based on kinds. Especially yangban Mask has more powerful nativeness than choraengi Mask, and is more interesting than jung Mask, baekjeong Mask, and bune Mask. Thirdly, the materials used in the products of hahae Mask generated differences of sensibility in elaborateness. Especially, elaborate image was emphasized about materials of glass. Fourthly, sensible image of hahae Mask was dependent upon population-statistic characteristics (age, sex, education) and characteristics of products(materials, kinds of Mask). If development of cultural products related with hahae Mask considers five sensible factors based on this study, it will contribute to development of design which coincides with consumers' needs.

• Journal of Convergence for Information Technology
• /
• v.9 no.1
• /
• pp.99-104
• /
• 2019

In an attempt to shed light on the effects of overseas internships on foreign language development, this study investigated the differences in English compositions written by 10 Korean university students who joined an overseas internship program for 15 weeks. For data collection, the participants each wrote an English composition before and after the internship. Data collected was analyzed to discern differences in the two writings, and statistical analyses were carried out of the results. Results showed that the participants appeared to have attained lexical fluency, generating longer sentences embedded with multisyllabic, more diverse types, more complex and less redundant words in more complicated structures after the internship. This study revealed that overseas internships facilitated the growth of linguistic abilities. Korean SMEs need to enhance the global capacity of their human resources via overseas internships to strengthen their global competitiveness, apart from improving their industrial competencies such as productivity and product quality.

• 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.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.213-218
• /
• 2019

기계독해는 자연어로 표현된 질문과 단락이 주어졌을 때, 해당 단락 내에 표현된 정답을 찾는 태스크이다. 최근 기계독해 태스크도 다른 자연어처리 태스크와 유사하게 BERT, XLNet, RoBERTa와 같이 사전에 학습한 언어모델을 이용하고 질문과 단락이 입력되었을 경우 정답의 경계를 추가 학습(fine-tuning)하는 방법이 우수한 성능을 보이고 있으며, 특히 KorQuAD v1.0 데이터셋에서 학습 및 평가하였을 경우 94% F1 이상의 높은 성능을 보이고 있다. 본 논문에서는 현재 최고 수준의 기계독해 기술이 학습셋과 유사한 평가셋이 아닌 일반적인 질문과 단락 쌍에 대해서 가지는 일반화 능력을 평가하고자 한다. 이를 위하여 첫번째로 한국어에 대해서 공개된 KorQuAD v1.0 데이터셋과 NIA v2017 데이터셋, 그리고 엑소브레인 과제에서 구축한 엑소브레인 v2018 데이터셋을 이용하여 데이터셋 간의 교차 평가를 수행하였다. 교차 평가결과, 각 데이터셋의 정답의 길이, 질문과 단락 사이의 오버랩 비율과 같은 데이터셋 통계와 일반화 성능이 서로 관련이 있음을 확인하였다. 다음으로 KorBERT 사전 학습 언어모델과 학습 가능한 기계독해 데이터 셋 21만 건 전체를 이용하여 학습한 기계독해 모델에 대해 블라인드 평가셋 평가를 수행하였다. 블라인드 평가로 일반분야에서 학습한 기계독해 모델의 법률분야 평가셋에서의 일반화 성능을 평가하고, 정답 단락을 읽고 질문을 생성하지 않고 질문을 먼저 생성한 후 정답 단락을 검색한 평가셋에서의 기계독해 성능을 평가하였다. 블라인드 평가 결과, 사전 학습 언어 모델을 사용하지 않은 기계독해 모델 대비 사전 학습 언어 모델을 사용하는 모델이 큰 폭의 일반화 성능을 보였으나, 정답의 길이가 길고 질문과 단락 사이 어휘 오버랩 비율이 낮은 평가셋에서는 아직 80%이하의 성능을 보임을 확인하였다. 본 논문의 실험 결과 기계 독해 태스크는 특성 상 질문과 정답 사이의 어휘 오버랩 및 정답의 길이에 따라 난이도 및 일반화 성능 차이가 발생함을 확인하였고, 일반적인 질문과 단락을 대상으로 하는 기계독해 모델 개발을 위해서는 다양한 유형의 평가셋에서 일반화 평가가 필요함을 확인하였다.

• Journal of the Korean Society for information Management
• /
• v.34 no.1
• /
• pp.31-50
• /
• 2017

This study was to suggest the problems and the improvement plan of Digital Library System (DLS) which has solved the library management and has supported the data building for resource sharing in school libraries since 2001. The 9 DLS committees were interviewed about the current situation of DLS use and the problems of DLS system in the 6 areas of acquisition, cataloging, circulation and discharge, inventory, library statistics, and searching interface as the research methods. Based on the interviews, the improvement plans were suggested as followed. In acquisition, it was to need the acquisition system development and online purchase for users. In cataloging, the improvement of data quality management, and indexes and vocabularies control for upgrade of searching function were needed. The advanced circulation speed in circulation, the restoration of discarded data in inventory and the exact statistic data in library statistics were need to improve the DLS. This study would contribute to the betterment of DLS and increase the use of DLS.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1112-1123
• /
• 2003

WSD(word sense disambiguation) is one of the most difficult problems in Korean information processing. The Bayesian model that used semantic information, extracted from definition corpus(1 million POS-tagged eojeol, Korean dictionary definitions), resulted in accuracy of 72.08% (nouns 78.12%, verbs 62.45%). This paper proposes the statistical WSD model using NPH(New Prior Probability of Homonym sense) and distance weights. We select 46 homonyms(30 nouns, 16 verbs) occurred high frequency in definition corpus, and then we experiment the model on 47,977 contexts from ‘21C Sejong Corpus’(3.5 million POS-tagged eojeol). The WSD model using NPH improves on accuracy to average 1.70% and the one using NPH and distance weights improves to 2.01%.

• Science of Emotion and Sensibility
• /
• v.12 no.4
• /
• pp.501-510
• /
• 2009

This study is to establish GUI (graphic user interface) in mobile touch phone for grooming user by using two dimensional emotion model determined by multi-dimensional scale method. The processes conducted in the research were as the followings: First of all, visceral, behavioral, and reflective factors of emotion (Norman, 2002) was defined from investigating the life styles of the Grooming users. Secondly, factor analysis was performed to extract the representative emotional words. In the third step, they were mapped into the two-dimensional emotion model through multi-dimensional scaling. Finally, the mapped emotional words were tried to be related to GUI factors of touch phones and normalizing their relation degree between 0 and 1. This study determined GUI factors significantly related to representative emotions described as special, self-centered, sophisticated, free, passionate, neat for application to mobile touch phone. This study determined the major emotion factors that should be considered the most important while designing the GUI factors.

• 재활복지
• /
• v.21 no.3
• /
• pp.187-207
• /
• 2017

The purpose of this study was to explore the characteristics of defining concrete and abstract nouns for the elderly. A total of 382 elderly participated in this study and they were classified into four age groups (i.e., over 55 to under 64, over 65 to under 74, over 75 to under 84, and over 85 year-old group). They performed the word definition task, composed of five concrete and five abstract nouns. The total scores and numbers and ratio of core/supplementary meanings were compared among four elderly groups. The frequency and ratio of error types were also examined. The results showed that all four groups had statistically significant differences in total scores, numbers and ratio of core and supplementary meaning of concrete noun definition task. In addition, abstract noun definition performances revealed group differences except the two groups (over 75 to under 84 and over 85-year-old group). The oldest group showed a sharp increase in error production. The highest ratio of error types were personal experience in over 55 to under 64-year-old group, and over 65 to under 74 year-old groups; and for the target word repetition in over 75 to under 84 year-old group; and no response in over 85 year-old group. In conclusion, both concrete and abstract word defining abilities had age-related deterioration. This decline results from impairment in spreading semantic knowledge within semantic network, which is vulnerable to aging. Characteristics of word definition for elderly can provide basic information to understand various neurolinguistic disorders associated with age.

• The Journal of Korean society of community based occupational therapy
• /
• v.8 no.3
• /
• pp.25-35
• /
• 2018

Objective : The purpose of this study was to identify changes in reading ability among children with Borderline Intelligence by applying an electronic media reading training protocol. Methods : A picture book reading training protocol was applied to 10 childrens with borderline intelligence using electronic media to improve reading skills. This protocol was performed for 10 session once a week. After the analysis of the content validity index about the protocol presented in this study, this prococol was applied to the subjects. To analyze the changes of the reading ability for the subjects, KNISE-BAAT type A and B reading test were used. Results : According to the tests taken before and after implementing, the Application of Picture Booking Training Protocol using Electronic Media there was a significant improvement in Reading ability (Understanding words, Completion sentence, Vocabulary selection, Vocabulary arrangement, Understanding short text). However, there was no significant difference in Oral Reading. Conclusion : Application of Picture Booking Training Protocol using Electronic Media may be used as a beneficial measure to improve the reading abilities of children with Borderline Intellectual.