• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.116-121
• /
• 1997

한국어 문장에서 술어의 역할이 매우 중요하기 때문에 술어의 하위범주화 정보는 한국어 분석 및 생성에서 필수적이다. 그러나 기존의 한국어 술어의 하위범주화 사전은 전문가의 사전지식이나 직관에 의존하여 만들어졌기 때문에 주관적이고 오류의 가능성이 높으며 많은 수작업이 필요했다. 또 영역에 독립적인 하위범주화 정보를 구축하는 작업은 매우 어렵기 때문에 응용영역에 맞는 하위범주화 정보를 쉽게 구축하는 방법이 요구되었다. 본 논문에서는 구문구조부착 말뭉치를 이용하여 전문가의 제한된 개입만으로 통계정보와 명사의 의미정보를 포함하는 술어의 하위범주화 정보 구축 방법을 제안한다.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.59-64
• /
• 2015

최근 온라인 텍스트 자료를 이용하여 대중의 의견을 분석하는 작업이 활발히 이루어지고 있다. 이러한 작업에는 주관적 방향성을 갖는 텍스트의 논증 구조와 중요 내용을 파악하는 과정이 필요하며, 자료의 양과 다양성이 급격히 증가하면서 그 과정의 자동화가 불가피해지고 있다. 본 연구에서는 정책에 대한 찬반 의견으로 구성된 한국어 텍스트 자료를 직접 구축하고, 글을 구성하는 기본 단위들 사이의 담화 관계를 정의하였다. 각 단위들 사이의 관계는 기계학습과 규칙 기반 방식을 이용하여 예측되고, 그 결과는 합성되어 하나의 글에 대응되는 트리 구조를 이룬다. 또한 텍스트의 구조상에서 주제문을 직접적으로 뒷받침하는 문장 혹은 절을 추출하여 글의 중요 내용을 얻고자 하였다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.160-163
• /
• 2022

감성 분석(sentiment analysis)은 자연어 문장에 나타나는 감정 상태나 주관적인 의견을 분석하는 작업이다. 최근에는 자연어 처리(Natural Language Processing) 작업에서 딥러닝 기반의 모델이 좋은 성능을 보여주고 있다. 하지만, 모델의 복잡한 구조 때문에 모델이 어떠한 근거(rationale)로 판단하였는지 해석하기 어려운 문제가 있다. 모델이 좋은 성능을 보여도 예측에 관한 판단 근거가 없으면 결과를 해석하기 어렵고, 모델에 대한 신뢰가 떨어진다. 본 논문에서는 한국어 감성 분석 작업에 대해 사후 해석 모델을 이용하여 모델의 예측 결과에 대한 근거를 추출하고, 추출한 근거 정보를 이용한 근거 임베딩을 사용하여 근거 정보를 통합하는 방법이 감성 분석 모델의 성능을 개선함을 보인다.

• The Journal of the Korea Contents Association
• /
• v.10 no.11
• /
• pp.30-37
• /
• 2010

It is very important to analyze online customer reviews, which are small documents of writing opinions or experiences about products or services, for both customers and companies because the customers can get good informations and the companies can establish good marketing strategies. In this paper, we did not propose only dependency network model which is tool for analyzing online customer reviews, but also designed and implemented the system based on the dependency network model. The dependency network model analyzes both subjective and objective sentences, so that it can represent relative importance and relationship between the nouns in the sentences. In the result of implementing, we recognized that relative importance and relationship between the features of products or services, which can not be mined by opinion mining, can be represented by the dependency network model.

• Archives of design research
• /
• v.15 no.3
• /
• pp.249-258
• /
• 2002

This study is about the effect on the user's cognitive stress by font size when they read on PDA(Personal Digital Assistant). The evaluation was done through both subjective evaluation and physiological one, which is brain wave test, while the research and analysis were focused on the relationship between the user's cognitive stress and font size. The two final results were found out as follows. 1) Font sizes, which were tested, were 8, 10, 12, 14, and 16 points. Among theses, font size 14 was the least stressful for the users, while the most stressful size was found out 8 points. 2) The cerebral cortex reaction according to the font size activated occipital lobe, parietal lobe of occipital visual area. Here we could come to a very Important conclusion that the smaller font size on mobile information appliances made users the more stressed.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.53-56
• /
• 1999

ITU-T 국제 표준화 기구에서 인터넷 폰과 화상회의를 목적으로 개발된 G.723.1 음성 부호화기는 잡음 구간에서의 전송률을 낮추기 위한 방법으로 VAD(Voice Activity Detector)와 CNG(Comfort Noise Generator)를 사용하고 있다 이중 VAD는 최종적으로 현재 프레임의 에너지 레벨을 비교하여 음성의 활동 유무를 판정하고 있다. 하지만 G.723.1 VAD에서는 보다 안정적인 판정을 위해 음성 활동 구간 사이에 삽입되어 있는 묵음 구간에 대해서는 거의 대부분 음성이 활동하는 영역으로 판정을 하고 있다. 따라서 본 논문에서는 묵음 구간에 대해 보다 정확한 판정을 통하여 기존의 방법에 비해 전송율을 더욱 감소시킬 수 있는 방법을 제안한다. 실험에서는 묵음구간을 길게 조절한 문장을 사용하여 측정한 결과 평균 $46.8\%$ 정도의 전송율을 감소시킬 수 있었으며, 주관적인 음질평가의 경우 음질의 열하는 거의 발생하지 않았다.

• Korean Journal of Cognitive Science
• /
• v.2 no.2
• /
• pp.309-339
• /
• 1990

The most common way that people communicate is by speaking or writing natural languages.But if people use computers in the modern technology,they should learn artificial programming languages.If computers could understand what people mean when people speak or type natural languages,people would use the computers more easily and naturally.but there is a problem.The language which people use has vagueness.For example,the convential computer system cant's handle the subjective feeling like 'tall' or 'young'.So peole must specify the exact threshold like 'more'than 25 ages'.We have developed the knowledge-based natural language question answering system which can handle sentences having fuzzy concepts by using blackboard model.Our goal of this research is to develop a portable question answering system as interface for database systems or understanding systems.

• Journal of Oral Medicine and Pain
• /
• v.31 no.1
• /
• pp.59-67
• /
• 2006

There exist patients complaining speech problem due to dysesthesia or anesthesia following dental surgical procedure accompanied by local anesthesia in clinical setting. However, it is not clear whether sensory problems in orofacial region may have an influence on motor speech abilities. The purpose of this study was to investigate whether transitory sensory impairment of mandibular nerve by local anesthesia may influence on the motor speech abilities and thus to evaluate possibility of distorted motor speech abilities due to dysesthesia of mandibular nerve. The subjects in this study consisted of 7 men and 3 women, whose right inferior alveolar nerve, lingual nerve and long buccal nerve was anesthetized by 1.8 mL lidocaine containing 1:100,000 epinephrine. All the subjects were instructed to self estimate degree of anesthesia on the affected region and speech discomfort with VAS before anesthesia, 30 seconds, 30, 60, 90, 120 and 150 minutes after anesthesia. In order to evaluate speech problems objectively, the words and sentences suggested to be read for testing speech speed, diadochokinetic rate, intonation, tremor and articulation were recorded according to the time and evaluated using a Computerized Speech $Lab^{(R)}$. Articulation was evaluated by a speech language clinician. The results of this study indicated that subjective discomfort of speech and depth of anesthesia was increased with time until 60 minutes after anesthesia and then decreased. Degree of subjective speech discomfort was correlated with depth of anesthesia self estimated by each subject. On the while, there was no significant difference in objective assessment item including speech speed, diadochokinetic rate, intonation and tremor. There was no change in articulation related with anesthesia. Based on the results of this study, it is not thought that sensory impairment of unilateral mandibular nerve deteriorates motor speech abilities in spite of individual's complaint of speech discomfort.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.24-33
• /
• 2001

this paper describes a baseline for an implementation of a corpus-based Korean TTS system. The conventional TTS systems using small-sized speech still generate machine-like synthetic speech. To overcome this problem we introduce the corpus-based TTS system which enables to generate natural synthetic speech without prosodic modifications. The corpus should be composed of a natural prosody of source speech and multiple instances of synthesis units. To make a phone level synthesis unit, we train a speech recognizer with the target speech, and then perform an automatic phoneme segmentation. We also detect the fine pitch period using Laryngo graph signals, which is used for prosodic feature extraction. For break strength allocation, 4 levels of break indices are decided as pause length and also attached to phones to reflect prosodic variations in phrase boundaries. To predict the break strength on texts, we utilize the statistical information of POS (Part-of-Speech) sequences. The best triphone sequences are selected by Viterbi search considering the minimization of accumulative Euclidean distance of concatenating distortion. To get high quality synthesis speech applicable to commercial purpose, we introduce a domain specific database. By adding domain specific database to general domain database, we can greatly improve the quality of synthetic speech on specific domain. From the subjective evaluation, the new Korean corpus-based TTS system shows better naturalness than the conventional demisyllable-based one.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.149-159
• /
• 2021

This study wanted to analyze the types of recognition of messages expressed in clothing for women in their 20s who wear a lot of clothing and fashion products with text. It was intended to provide basic data necessary for the production of typography clothing and fashion products by considering the subjective evaluation of how women in their 20s type the characters expressed in fashion and the characteristics of each type. This study was conducted with the Q method, and the QUANL pc program was used for analysis. Type I thought that letters were a design element and fashion, and the characters expressed in clothes were recognized as images. Type 2 thought it was important that the characters expressed in the clothing were recognized as messages, and that the characters had social messages and period reflections. Type 3 preferred that letters be combined with casual clothes and valued the formability of the characters. Type 4 preferred characters to represent brands and liked to be placed in large positions. In the future, it is thought that additional research by various age groups and genders and detailed research should be conducted to identify differences in font, color, and sentence length.