• Journal of KIISE:Databases
• /
• v.34 no.6
• /
• pp.554-563
• /
• 2007

The e-Marketplace is growing rapidly and providing a more complex relationship between providers and consumers. In recent years, e-Marketplace integration or cooperation issues have become an important issue in e-Business. The e-Catalog is a key factor in e-Business, which means an e-Catalog System needs to contain more large data and requires a more efficient retrieval system. This paper focuses on designing an efficient retrieval system for very large e-Catalogs of large e-Marketplaces. For this reason, a new similarity measure for e-Catalog retrieval based on semantic relationships was proposed. Our achievement is this: first, a new e-Catalog data model based on semantic relationships was designed. Second, the model was extended by considering lexical features (Especially, focus on Korean). Third, the factors affecting similarity with the model was defined. Fourth, from the factors, we finally defined a new similarity measure, realized the system and verified it through experimentation.

• Journal of Korean Society of Archives and Records Management
• /
• v.23 no.4
• /
• pp.159-178
• /
• 2023

A digital archive is an online platform for preserving and utilizing digital records worthy of continued preservation. However, there are no shared standards for functionality, metadata, or data technical principles across digital archives in Korea. These issues create challenges in linking distributed digital records. This study proposes a common vocabulary for digital archives to enhance the interoperability of digital records and evaluates the interoperability of the digital archive built with the common vocabulary. We collect and analyze data from the digital archive on the Korean financial crisis of 1997 to construct a knowledge graph and compare its interoperability with the knowledge graph built with RiC-O. The archive and the knowledge graph underwent evaluation using the FAIR data principles evaluation framework. The constructed knowledge graph links various objects in the archive and provides contextual information to aid in understanding the archive. The results demonstrate that a knowledge graph built with a common vocabulary significantly improves the linkage, search, and interoperability of digital records compared to a traditional archive.

• Phonetics and Speech Sciences
• /
• v.14 no.3
• /
• pp.41-49
• /
• 2022

The average acoustic distribution of American English speakers was statistically compared with the English-speaking patterns of gifted students in a Science Academy in Korea. By analyzing speech recordings, the duration time of which is much longer than in previous studies, this research identified the degree of acoustic proximity between the two parties and the predictability of English academic achievement of gifted high school students. Long-term spectral acoustic power distribution vectors were obtained for 2,048 center frequencies in the range of 20 Hz to 20,000 Hz by applying an long-term average speech spectrum (LTASS) MATLAB code. Three more variables were statistically compared to discover additional indices that can predict future English academic achievement: the receptive vocabulary size test, the cumulative vocabulary scores of English formative assessment, and the English Speaking Proficiency Test scores. Linear regression and correlational analyses between the four variables showed that the receptive vocabulary size test and the low-frequency vocabulary formative assessments which require both lexical and domain-specific science background knowledge are relatively more significant variables than a basic suprasegmental level English fluency in the predictability of gifted students' academic achievement.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.679-682
• /
• 2007

This study aims to select the proper vocabularies for evaluation about the noise emission from water supply and drain installations in apartment bathroom. As a result of surveying overlapping vocabularies and scores of them for each sound sources, 'annoying', 'noisy', 'dynamic' and 'strident' are main unpleasant vocabularies to the noise from water supply and drain installations in apartment bathroom. And vocabularies such as 'dynamic', 'sudden', 'loudness', 'noisy' are classified into the first factor by analysis.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.242-247
• /
• 2007

After the Industrialization of 1960s, while it has greatly contributed to the industrial development owing to acceleration of mechanization, but it is real situation that the countermeasure to Noise Damage generating at the loud noise workshop is scarcely made. Especially, the Instrument-Noise made at factory and workplace is so shocking and repeatedly reiterating terrible noise that most of the spot workers are forcedly imposing such dangers as the severe unpleasant feeling and hearing impairments. On such point of view, this Research has attempted to extract the proper Rating Vocabulary in order for valuation on Instrument Noise made at the terrible noise-workplace, therefore it is considering that those extracted Vocabularies could be utilized as the useful materials for appraisal on Instrument Noise, also for establishment of Regulation-Standard with regard to Acoustic Psychology Experimentation and Instrument Noise.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.2
• /
• pp.84-89
• /
• 1998

본 논문에서는 임의의 단어를 인식하기 위하여 음성학적으로 최적화된 (phonetically-optimized word) 음성 데이터베이스를 사용하여 훈련된 가변어휘 고립단위 음 성인식기의 실제 인식기 사용 환경에서의 성능을 평가하였다. 이를 위하여, 훈련 데이터베이 스에서와 상이한 환경에서 수집된 음성학적으로 균형 잡힌(phonetically-balanced word) 고 립 단어 음성을 테스트 데이터로 사용하였다. 테스트 데이터는 일반적인 사무실에서 작동하 는 노트북 PC에서 내장 마이크를 사용하여 녹음되었다. 이렇게 녹음된 음성을 사용하여 고 립단어 인식기의 인식률을 측정하였다. 이 인식기는 최대 사후(maximum a posteriori) 추정 알고리듬을 사용하여 화자의 변화에 적응하였다. 컴퓨터 모의실험 결과에 의하면 화자 적응 을 하지 않은 기본 시스템은 깨끗한 음성에 대하여 81.3%에서 사무실 환경 음성에 대하여 69.8%로 인식률이 저하되었다. 사무실 환경 음성에 대하여, 비교사 점진(unsupervised incremental) 모드에서 최대 사후 추정 화자 적응 알고리듬을 적용하였을 경우에는 화자적 응을 하지 않은 경우에 비하여 9%의 에러를 감소시키며, 50단어의 적응 단어를 사용하여 교사 묶음(supervised batch) 모드에서 최대 사후 추정 화자 적응 알고리듬을 적용하였을 경우에는 16%의 에러를 감소시켰다.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.7
• /
• pp.626-631
• /
• 2004

In this study, the extracted words from the former study such as annoying, loud, noisy, irritating, disagreeable, strident, disturbed, and dissonant are given to subjects in psycho acoustic experiment lab. And then, correlation analysis between the words and floor impact noise rating method were carried out. As a result of this study followings are suggested ‘Annoying’ is the word most accurately expressing the subjects’ unpleasant feeling of domestic floor impact noise. The results of this study could be basic materials for psycho acoustic experiments for criteria on floor impact noise and Sound Classification on Floor Impact Sound Insulation Performance.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.1697-1698
• /
• 2013

정보처리 기술이 발전함에 따라 정보에 대한 접근과 소통은 더욱 빠르고 편리하게 되었고, 동시에 사용자의 정보에 대한 요구 또한 세분화되고 다양해지면서, 이러한 다양한 요구에 대응하기 위해서 사용자의 경험과 소통하여 인지과정에 영향을 줄 수 있는 감성이 중요하게 인식되고 있다. 감성은 동일한 외부자극에 대해 개인의 경험, 환경 등에 따라 다르게 나타나기 때문에 객관적으로 측정하기가 어렵지만, 외부자극에 대해 반사적이고 직관적으로 발생하여 의사결정 과정에 지속적으로 영향을 주기 때문에 사용자의 경험과 소통하여 사용자의 요구를 이해할 수 있는 정보를 제공한다. 본 논문에서는 이미지 공유 사이트를 이용하여 이미지라는 외부자극에 대해 사용자들이 느낀 어휘들을 수집하고 긍정과 부정 감성을 분석하여 어휘를 기반으로 이미지의 감성을 측정하고 평가하였다.

• 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.

• Science of Emotion and Sensibility
• /
• v.19 no.3
• /
• pp.103-120
• /
• 2016

This study investigated how video playback styles affect viewers' emotional responses to a video and then suggested emotion assessment tool for playback-edited videos. The study involved two in-lab experiments. In the first experiment, observers were asked to express their feelings while watching videos in both original playback and articulated playback simultaneously. By controlling the speed, direction, and continuity, total of twelve playback styles were created. Each of the twelve playback styles were applied to five kinds of original videos that contains happy, anger, sad, relaxed, and neutral emotion. Thirty college students participated and more than 3,800 words were collected. The collected words were comprised of 899 kinds of emotion terms, and these emotion terms were classified into 52 emotion categories. The second experiment was conducted to develop proper emotion assessment tool for playback-edited video. Total of 38 emotion terms, which were extracted from 899 emotion terms, were employed from the first experiment and used as a scales (given in Korean and scored on a 5-point Likert scale) to assess the affective quality of pre-made video materials. The total of eleven pre-made commercial videos which applied different playback styles were collected. The videos were transformed to initial (un-edited) condition, and participants were evaluated pre-made videos by comparing initial condition videos simultaneously. Thirty college students evaluated playback-edited video in the second study. Based on the judgements, four factors were extracted through the factor analysis, and they were labelled "Happy", "Sad", "Reflective" and "Weird (funny and at the same time weird)." Differently from conventional emotion framework, the positivity and negativity of the valence dimension were independently treated, while the arousal aspect was marginally recognized. With four factors from the second experiment, finally emotion assessment tool for playback-edited video was proposed. The practical value and application of emotion assessment tool were also discussed.