• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.67-71
• /
• 2016

본 논문에서는 word2vec과 doc2vec을 함께 CNN에 적용한 문서 분류 방안을 제안한다. 먼저 어절, 형태소, WPM(Word Piece Model)을 각각 사용하여 생성한 토큰(token)으로 doc2vec을 활용하여 문서를 vector로 표현한 후, 초보적인 문서 분류에 적용한 결과 WPM이 분류율 79.5%가 되어 3가지 방법 중 최고 성능을 보였다. 다음으로 CNN의 입력자질로써 WPM을 이용하여 생성한 토큰을 활용한 word2vec을 범주 10개의 문서 분류에 사용한 실험과 doc2vec을 함께 사용한 실험을 수행하였다. 실험 결과 word2vec만을 활용하였을 때 86.89%의 분류율을 얻었고, doc2vec을 함께 적용한 결과 89.51%의 분류율을 얻었다. 따라서 제안한 모델을 통해서 분류율이 2.62% 향상됨을 확인하였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.209-212
• /
• 2017

고도화된 머신러닝과 딥러닝 기술은 영상처리, 자연어처리 등의 분야에서 많은 문제를 해결하고 있다. 특히 사용자가 입력한 문장을 분석하고 그에 따른 문장을 생성하는 자연어처리 기술은 기계 번역, 자동 요약, 자동 오류 수정 등에 널리 이용되고 있다. 딥러닝 기반의 자연어처리 기술은 학습을 위해 여러 계층의 신경망을 구성하여 단어 간 의존 관계와 문장 구조를 학습한다. 그러나 학습 과정에서의 계산양이 방대하여 모델을 구성하는데 시간과 비용이 많이 필요하다. 그러나 Word2Vec 모델은 신경망과 유사하게 학습하면서도 선형 구조를 가지고 있어 딥러닝 기반 자연어처리 기술에 비해 적은 시간 복잡도로 고차원의 단어 벡터를 계산할 수 있다. 따라서 본 논문에서는 Word2Vec 모델을 활용하여 한국어 문장을 생성하는 방법을 제시하였다. 본 논문에서는 지정된 문장 템플릿에 유사도가 높은 각 단어들을 적용하여 문장을 구성하는 Word2Vec 모델을 설계하였고, 서로 다른 학습 데이터로부터 생성된 문장을 평가하고 제안한 모델의 활용 방안을 제시하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2E
• /
• pp.27-31
• /
• 1997

This paper proposes a new rejection algorithm which distinguishes unregistered spoken words(or non-keywords) from registered vocabulary. Two kinds of garbage models are employed in this design ; the original garbage model and a new word garbage model. The original garbage model collects all non-keyword patterns where the new word garbage model collects patterns classified by recognizing each non-keyword pattern with registered vocabulary. These two types of garbage models work together to make a robust reject decision. The first stage of processing is the classification of an input pattern through the original garbage model. In the event that the first stage of processing is ambiguous, the new word dependent garbage model is used to classify thye input pattern as either a registered or non-registered word. This paper shows the efficiency of the new word dependent garbage model. A Dynamic Multisection method is used to test the performance of the algorithm. Results of this experiment show that the proposed algorithm performs at a higher level than that of the original garbage model.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.136-146
• /
• 1995

In this paper, a Japanese morphological analyzer for Japanese to Korean Machine Translation System is designed. The analyzer reconstructs the Japanese input sentence into word phrases that include grammatical and dictionary informations. Thus we propose the algorithm to separate morphemes and then connect them by reference to a corresponding Korean word phrases. And we define the connector to control Japanese word phrases It is used in controlling the start and the end point of the word phrase in the Japanese sentence which is without a space. The proposed analyzer uses the analysis dictionary to perform more efficient analysis than the existing analyzer. And we can decrease the number of its dictionary searches. Since the analyzer, proposed in this paper, for Japanese to Korean Machine Translation System processes each word phrase in consideration of the corresponding Korean word phrase, it can generate more accurate Korean expressions than the existing one which places great importance on the generation of the entire sentence structure.

• English Language & Literature Teaching
• /
• v.10 no.3
• /
• pp.159-175
• /
• 2004

This paper investigated the types of errors on English pronunciation and intelligibility of Korean EFL students, and the relationship between the pronunciation accuracy and intelligibility. Thirty one students were evaluated by six English native speakers in terms of overall intelligibility and accuracy In five areas such as nuclear stress, word stress, syllable structure, consonants and vowels. According to the findings of the study, pronunciation errors were made by the subjects more frequently In word stress than any other area of pronunciation accuracy. The Pearson correlation analysis showed that intelligibility was related with word stress, syllable structure, consonants and vowels, and the stepwise multiple regression analysis indicated that, among the above five areas of pronunciation accuracy, word stress best accounted for the intelligibility of a given sentence. In the conclusion, the importance of teaching pronunciation of in those five areas with a special focus on word stress was emphasized m terms of intelligibility.

• Journal of the Korean Home Economics Association
• /
• v.41 no.11
• /
• pp.189-200
• /
• 2003

The purpose of this study was to investigate that positive and negative word-of-mouth informations getting hairshop customers have influence on visiting intention of potential consumers. Data were collected from 354 university or college women. The results showed as follows; First, positive word-of-mouth informations that consumers have experienced in using hairshop were employee altitude/technique, consideration in customer's situation, kindness, saving of time/additional service, facilities, rational price, gift service/benefit in conditions of location. Second, negative word-of-mouth informations that consumers have experienced in using hairshop were inconsistent service, service focus on non-customers, irrational price/technique insufficiency/ inadequate compensational system, irrelevance of face-to-face management. Third, in getting positive word-of-mouth informations, consideration in customer's situation, rational price and gift service/benefit in conditions of location, consumers had visiting intention, and in getting negative informations, irrational price/technique insufficiency/inadequate compensational system, consumers had no visiting intention.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.747-751
• /
• 2010

This paper proposes the method that increases the accuracy for tagging word meaning by creating sense tagged data automatically using machine readable dictionaries. The concept of meaning group is applied here, where the meaning group for each meaning of a target word consists of neighbor words of the target word. To enhance the tagging accuracy, the notion of concentration is used for the weight of each word in a meaning group. The tagging result in SENSEVAL-2 data shows that accuracy of the proposed method is better than that of existing ones.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.51-67
• /
• 2004

The objective of this study was to investigate the effects in auditory performance and vocal development of Onomatopoeia and Mimetic Word Productive Training Program in prelingually deafened children with cochlear implantation. The effects were measured with Lip-profile (Listening progress profile: LiP), the number of utterances, vocal developmental level and phonetic inventory. Subjects were four children with cochlear implants who were able to detect speech sounds and environmental sounds. The Onomatopoeia and Mimetic word Productive Training Program was made up of 3 steps with 24 Onomatopoeia and Mimetic words. This study was pre and post design. The results of the study were as follows: First, after Onomatopoeia and Mimetic word Productive Training Program was treated, LiP score was significantly higher. Second, after this program was treated, the number of utterances and emergence of both canonical and postcanonical utterances were increased. Emergence of vowel and consonant Features were increased and diversified. In conclusion, Onomatopoeia and Mimetic Word Productive Training Program appeared to facilitate efficient auditory performance and vocal development.

• Research in Mathematical Education
• /
• v.9 no.1 s.21
• /
• pp.1-9
• /
• 2005

This paper investigates instructional strategies with potential for improving students' achievement in word problem solving. This review compares and analyzes the direct instruction (DI) and cognitively guided instruction (CGI) research on K-3 word problem solving mathematics students in a demonstration of my position that teachers need to understand student mathematical thinking to enhance students' achievement in word problem solving. CGI provides a more appropriate instructional model than DI for teaching word problem solving. For example, student-centered, conceptual understanding, and children's informal or invented problem solving strategies communicating with each other mathematically, etc. Korean teachers and teacher educators need to consider implementing CGI teaching strategies.

• Annual Conference on Human and Language Technology
• /
• 1999.10e
• /
• pp.156-163
• /
• 1999

최근의 자연어 처리 분야의 연구들에서 광범위하고 완전한 어휘 지식 베이스의 필요성이 입증되었다. 영어권의 경우, 이에 대한 연구가 오래 전부터 있어 왔고, 그 결과로 현재 주로 사용되고 있는 개념체계에는 Roget's Thesaurus와 WordNet 등이 있다. 이러한 개념체계들은 자연어 처리의 여러 응용 분야에서 중요한 역할을 담담하고 있지만, 다른 언어의 경우 널리 사용되고 있는 개념체계가 없는 실정이다. 본 논문에서는 Princeton 대학의 WordNet을 기반으로 한영 사전과 국어 사전을 이용하여 한국어 명사의 개념체계를 자동으로 구축함으로써, 이미 구축되어진 다른 언어의 개념체계를 이용하여 새로운 언어의 개념체계를 자동으로 구축할 수 있음을 보인다. 먼저 한영 사전과 국어 사전으로부터 뽑아낸 한국어 단어 일부의 의미를 다양한 WSD(Word Sense Disambiguation) 방법을 적용시켜 WordNet의 synset에 자동으로 연결시킬 수 있음을 보인다. 그리고 각각의 자동변환으로 나온 결과들에 대해서 적용율과 정확도를 비교하도록 한다.