• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.146-154
• /
• 2001

본 논문에서는 개념망 구축을 위해 사전 뜻풀이말에서 추출 가능한 의미속성의 분포 정보를 기반으로 어휘 연관도를 측정하고자 한다. 먼저 112,000여 개의 사전 뜻풀이말을 대상으로 품사 태그와 의미 태그가 부여된 코퍼스에서 의미속성을 추출한다. 추출 가능한 의미속성은 체언류, 부사류, 용언류 등이 있는데 본 논문에서는 일차적으로 명사류와 수식 관계에 있는 용언류 중 관형형 전성어미('ㄴ/은/는')가 부착된 것을 대상으로 한다. 추출된 공기쌍 45,000여 개를 대상으로 정제 작업을 거쳐 정보이론의 상호 정보량(MI)을 이용하여 명사류와 용언류의 연관도를 측정한다. 한편, 자료의 희귀성을 완화하기 위해 수식 관계의 명사류와 용언류는 기초어휘를 중심으로 유사어 집합으로 묶어서 작업을 하였다. 이러한 의미속성의 분포 정보를 통해 측정된 어휘 연관도는 의미속성의 공유 정도를 계산하여 개념들간에 계층구조를 구축하는 데 이용할 수 있다.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.139-140
• /
• 2017

본 연구는 공과대학 학생들이 배우는 전공영어로서의 특수목적영어(ESP)에 대해 코퍼스 기반 접근법의 유용성을 논하고자 한다. 이에 본 연구에서는 공과대학에서 사용하는 전공텍스트를 코퍼스로 구축하여 컴퓨터에 기반한 분석에서 나온 결과들을 제시하면서 공학영어 코퍼스의 특성을 살펴보고 궁극적으로 영어매개수업을 듣는 공대학생들의 데이터 기반 학습에 일조하고자 한다. 본 연구에서 사용된 목표 코퍼스는 세부전공과 상관없이 공통적으로 적용되는 공학과목을 선정하여 구축되었고 비교대상인 참조 코퍼스는 British National Corpus를 사용하였다. 공학영어 코퍼스는 총 단어 180만개, 단어 유형 만 6천여개로 이루어졌고 코퍼스 분석도구인 AntConc 3.4.4를 이용하여 빈도 분석과 키워드 분석이 수행되었다. 고빈도수 어휘의 분석결과 목표 코퍼스와 참조 코퍼스에서 가장 빈번하게 나타나는 어휘군은 내용어(content words)보다는 기능어(function words) 형태가 많다는 점이 나타났고 내용어군만 분석결과 참조코퍼스에 비해 공학영어 코퍼스에 과학영역의 변이어가 많이 분포하고 있음이 드러났다. 또한 키워드 분석에서는 공학영어 코퍼스의 키워드 동사군이 전문적인 어휘(technical vocabulary)보다는 비전문적인 학술적 어휘(non-technical academic vocabulary)가 상대적으로 많이 분포되어 있음이 드러나 ESP교육을 실시함에 있어서 전공관련 전문영어와 함께 일반적인 학술 영어에 대한 인식을 고양해야 할 필요성이 대두된다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.127-134
• /
• 2010

In continuous vocabulary recognition system by probability distribution of clustering method has used model parameters of an advance estimate to generated each contexts for phoneme data surely needed but it has it's bad points of gaussian model the accuracy unsecure of composed model for phoneme data. To improve suggested probability distribution mixed gaussian model to optimized that phoneme data search supported configuration thread system. This paper of configuration thread system has used extension facet classification user phoneme configuration thread information offered gaussian model the accuracy secure. System performance as a result of represent vocabulary dependence recognition rate of 98.31%, vocabulary independence recognition rate of 97.63%.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.295-300
• /
• 2015

In vocabulary recognition using an HMM model which models the prior distribution for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate. The Bayesian techniques to improve vocabulary recognition model, it is proposed using a convergence of two methods to improve recognition noise-canceling recognition. In this paper, using a convergence of the prior probability method and techniques of Bayesian posterior probability based on HMM remove noise and improves the recognition rate. The result of applying the proposed method, the recognition rate of 97.9% in vocabulary recognition, respectively.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.426-435
• /
• 2021

This study aims to functionally classify lexical bundles appearing in academic papers on nuclear science and engineering written in English and then analyze the lexical bundles' characteristics compared to those appearing in general academic papers. To this end, the texts of nuclear science and engineering papers were collected and produced as a corpus(c. 1 mil. tokens). Then they were statistically compared through Chi-square tests and standardized residuals with the corpus of general academic papers(c. 750,000 tokens). The results revealed that, compared to general academic papers, the bundles in the stance lexical bundle category were mainly used among the functional lexical bundle in nuclear science and engineering. The use of the lexical bundles lacked much variety. The same type of lexical bundles was 're-used' and 'recycled'. Based on these research results, educational implications for English for Academic Purposes and the further direction of follow-up research were discussed and suggested.

• 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.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.273-278
• /
• 2014

In vocabulary recognition using HMM(Hidden Markov Model) by model for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate. Improve them with a HMM model is proposed for the optimization of the Bayesian methods. In this paper is posterior distribution and prior distribution in recognition Gaussian mixtures model provides a model to optimize of the Bayesian methods vocabulary recognition. The result of applying the proposed method, the recognition rate of 97.9% in vocabulary recognition, respectively.

• Phonetics and Speech Sciences
• /
• v.15 no.1
• /
• pp.9-17
• /
• 2023

The purpose of this study is to determine how the Korean diphthong /jo/ shows phonetic variation in various linguistic environments. The pronunciation of /jo/ is discussed, focusing on the relationship between phonetic variation and the distribution range of vowels. The location in a word (monosyllable, word-initial, word-medial, word-final) and word class (content word, function word) were analyzed using the speech of 10 female speakers of the Seoul Corpus. As a result of determining the frequency of appearance of /jo/ in each environment, the pronunciation type and word class were affected by the location in a word. Frequent phonetic reduction was observed in the function word /jo/ in the acoustic analysis. The word class did not change the average phonetic values of /jo/, but changed the distribution of individual tokens. These results indicate that the linguistic environment affects the phonetic distribution of vowels.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.21-24
• /
• 1999

본 논문에서는 가변어휘 음성인식기의 성능개선 작업에 관한 내용을 기술하고 있다. 묵음을 포함한 총 40개의 문맥독립 음소모델을 사용한다. LDA 기법을 이용하여 동일차수의 특징벡터내에 보다 유용한 정보를 포함시키고, likelihood 계산시 가우시안 분포와 mixture weight에 대한 가중치를 달리 함으로써 성능향상을 볼 수 있었다. ETRI POW 3848 DB만을 사용하여 실험한 경우, $21.7\%$의 오류율 감소를 확인할 수 있었다. 잡음환경 및 어휘독립환경을 고려하여 POW 3848 DB와 PC 168 DB 및 PBW445 DB를 사용한 실험도 행하였으며, PBW 445 DB를 사용한 어휘독립 인식실험의 경우 $56.8\%$의 오류율 감소를 얻을 수 있었다.

• Journal of the Korean Chemical Society
• /
• v.54 no.4
• /
• pp.471-478
• /
• 2010

This study analyzed the vocabulary level in the 'Water' unit of chemistry I textbook. It also analyzed its relevance to the 11th graders' vocabulary level. The main tool for analyzing vocabulary level was SWA(Science Word Analysis) program which was referenced the Standard Korean Dictionary and Graduated Vocabulary of Korean Language Education. The results in this study turned out to be as follows: The distribution of scientific vocabulary level increased from Level-1 to Level-3 and showed a tendency to decrease from Level-3 until Level-5. The average percentage of Out of level is the largest as 37%. The highest percentage of non-scientific vocabulary was Level-1. The distribution of non-scientific vocabulary level decreased progressively. The Level-5 and Out of level are used 18% averagely. So, there are 6 vocabularies of Level-5 and 82 vocabularies of extra-level inappropriate in scientific vocabularies. And there are 53 vocabularies of Level-5 and 145 vocabularies of Out of level inappropriate in non-scientific vocabularies. Therefore, the overall state of textbooks for grade 11 students are reasonable. But there are a great many vocabularies inappropriate for them. Those should be used minimum, and to be changed to the 1-4 of level vocabulary as stated in the student's level of understanding of appropriate vocabulary.