• 한국언어정보학회지:언어와정보
• /
• 제18권1호
• /
• pp.77-97
• /
• 2014

Multilingual machine translation means the machine translation that is for more than two languages. Common transfer means the transfer in which we can reuse the transfer rules among similar languages according to linguistic typology. Therefore, the multilingual machine translation based on common transfer is the multilingual machine translation that can share the transfer rules among languages with similar linguistic typology. This paper describes the linguistic modeling for multilingual machine translation based on common transfer under development. This linguistic modeling consists of the linguistic devices such as 1) multilingual common Part-of-Speech set, 2) multilingual common transfer format, 3) multilingual common transfer chunking, and 4) multilingual common transfer rules based on linguistic typology. Validity of this linguistic modeling for multilingual machine translation is shown in the simulation. The multilingual machine translation system based on common transfer including Korean, English, Chinese, Spanish, and French will be developed till 2018.

• 한국정보처리학회논문지
• /
• 제6권12호
• /
• pp.3539-3547
• /
• 1999

KANT(Knowledge-based Accurate Natural language Translation) 시스템 생성 엔진을 위한 한국어 언어 정보를 구축하였다. KANT 시스템은 언어 중립적인 생성 엔진을 갖고 있기 때문에 한국어 언어 정보의 구축은 사실상 한국어 생성 모듈의 개발을 의미한다. 구축된 언어 정보는 개념별 한국어 대응 규칙, 범주별 한국어 대응 규칙, 한국어 사전 및 템플리트 선언, 한국어 문법 규칙, 한국어 어휘 유형, 한국어 어휘 규칙, 한국어 다시 쓰기 규칙 등으로 구성된다. 구축된 언어 정보를 이용해 KANT 시스템 개발 측이 준비한 118 문장 분량의 중간 언어 표현로부터 106 문장을 올바르며 완전한 한국어 문장으로서 생성하였다.

• 인문언어
• /
• 제1권2호
• /
• pp.123-139
• /
• 2001

In the history of linguistics in the world the scholars in India could be regarded as the representative linguists, who had provided the cornerstone of the academic development at linguistics. Without looking into the contents of Indian linguistic theories devised and developed in the past it would be almost impossible to account for the origin of descriptive linguistics and historical linguistics. These linguistics trends became full-fledged in 19 and 20 century and are still accepted by a lot of researchers in order to analyze newly revealed languages and train students only coming up the toddling level of linguistic studies. In this paper I will show how far the influence of Indian linguistics has colored the flow of linguistic growth historically. Especially through the analysis of Panini grammar I will prove the intimate relationship between the Indian linguistic theory and the generative grammar - it is the most active theory at present. The methods that Panini applied to constitute the rules like sutra include lots of information, that also could be discovered at the rules postulated in the generative grammar. One of the common features found at both linguistic theories is the simplicity of rule representation. At the generative grammar a rule has to be established without any redundancy. When certain number of sounds like p, b, m show the same phonological. change relevant to lips (labial in linguistic term) different rules need not to be given for each sound separately. It is better to find a way of putting the sounds together in a rule with grouping the 3 sounds with the shared phonetic feature 'labial'. In Panini grammar the form of a rule was decided based on the simplicity, too. For example, sutra 6.1.77 shows the phonological connection between the vowels i, u r 1 and the semi-vowels y, v, r, 1. However, it does not require to postulate 4 individual rules respectively. Instead a rule in which the vowels and the semi-vowels are involved is suggested, and linguistically the rule make it clear that the more simpler the rules will be the better they can reflect the efficiency of human language acquisition. Although the systems introduced at Panini grammar have some sense of distance from the language education itself we cannot deny the fact that the grammar formulates the a turning point of linguistic development. It is essential for us to think over the grammar from the view point of the modem linguistic theories to understand their root and trunk more thoroughly. It will also help us to predict in which way linguistic tendency will proceed to in future.

• Journal of Electrical Engineering and Technology
• /
• 제11권2호
• /
• pp.309-319
• /
• 2016

This paper presents a new recognition and classification method for power quality (PQ) disturbances on the basis of pattern linguistic values. This method solves the difficulty of recognizing disturbances rapidly and accurately by using fuzzy logic. This method uses classification disturbance patterns to define the linguistic values of fuzzy input variables and used the input variables of corresponding disturbance pattern to set membership functions. This method also sets the fuzzy rules by analyzing the distribution regularities of the input variable values. One characteristic of this method is that the linguistic values of fuzzy input variables and the setting of membership functions are not only related to the input variables but also to the character of classification disturbance and the classification results. Furthermore, the number of fuzzy rules is equal to the number of disturbance patterns. By using this method for disturbance classification, the membership function and design of fuzzy rules are directly related to the objective of classification, thus effectively reducing the complexity of the design process and yielding accurate classification results. The classification results of the simulation and measured data verify the feasibility and effectiveness of this method.

• The Journal of the Acoustical Society of Korea
• /
• 제16권1E호
• /
• pp.64-74
• /
• 1997

In many decision making systems, rule-based approaches are used to solve complex problems in the areas of pattern analysis and computer vision. In this paper, we present methods for generating fuzzy IF-THEN rules automatically from training data for pattern classification and high-level computer vision. The rules are generated by construction minimal approximate fuzzy aggregation networks and then training the networks using gradient descent methods. The training data that represent features are treated as linguistic variables that appear in the antecedent clauses of the rules. Methods to generate the corresponding linguistic labels(values) and their membership functions are presented. In addition, an inference procedure is employed to deduce conclusions from information presented to our rule-base. Two experimental results involving synthetic and real are given.

• 한국항해학회지
• /
• 제5권2호
• /
• pp.59-88
• /
• 1981

Many studies have been done in the field of fuzzy logic theory, but it's application is not so much, and particularly, there isn't any application to the ship's steering system, until now. This paper is to survey the effect of application of fuzzy logic control to the ship's steering system. The controller is made up of a set of Linguistic Control Rules which are conditional linguistic statements connecting the inputs and the output, and take the inputs derived from the errors, that is, deviation angle and it's angular velocity. These two variables together give information about the state of the steering system, and the Linguistic Control Rules are implemented on the digital computer. The characteristics of this system were investigated through the computer simulation and satisfactory results compared with that of the conventional PD controller were obtained.

• 한국항해학회지
• /
• 제8권1호
• /
• pp.15-42
• /
• 1984

Many studies have been done in the field of fuzzy logic theory, but it's application to the ship's steering system is few until this date. This paper is to survey the effect of application of fuzzy logic control by new compositional rule of Inference to the ship's steering system. The controller is made up of a set of Linguistic Control Rules which are conditional linguistic statements connecting the inputs and output, and take the inputs derived from deviation angle and it's angular velocity. The Linguistic Control Rules are implemented on the digital computer to verify the performance of the fuzzy logic controller and simulations have been done in six cases of initial condition and disturbance type. Consequently, it was proved that the ship's steering system by introducing the F.L.C. is performed efficiently and less energy loss system compared with the conventional autopilot.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.258-263
• /
• 1998

Fuzzy rules are often obtained by experts who know an objective system well. fuzzy rules acquired by experts, however, do not express all input-output relations of the system. This paper proposes a method fuzzy rules are expressed in plain language so that the fuzzy rules are understood easily. The proposed method is applied to the control of the distance between cars and running through a crank-typed road, and the validity of the method is confirmed.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1082-1085
• /
• 1993

In this paper, we notice the fact that a human learning process is characterized by a process under a natural language environment, and discuss an approach of learning based on indirect linguistic instructions. An instruction is interpreted through some meaning elements and each trend. Fuzzy evaluation rule are constructed for the searched meaning elements of the given instruction, and the performance of a system to be learned is improved by the evaluation rules. In this paper, we propose a framework of learning based on indirect linguistic instruction based learning using fuzzy theory: FULLINS(FUzzy-Learning based on Linguistic IN-Struction). The validity of FULLINS is shown by applying it to helicopter flight control.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권3호
• /
• pp.125-132
• /
• 2022

문장 압축은 원본 문장의 중요한 의미는 유지하면서 길이가 축소된 압축 문장을 생성하는 자연어처리 태스크이다. 문법적으로 적절한 문장 압축을 위해, 초기 연구들은 사람이 정의한 언어 규칙을 활용하였다. 또한 시퀀스-투-시퀀스 모델이 기계 번역과 같은 다양한 자연어처리 태스크에서 좋은 성능을 보이면서, 이를 문장 압축에 활용하고자 하는 연구들도 존재했다. 하지만 언어 규칙을 활용하는 연구의 경우 모든 언어 규칙을 정의하는 데에 큰 비용이 들고, 시퀀스-투-시퀀스 모델 기반 연구의 경우 학습을 위해 대량의 데이터셋이 필요하다는 문제점이 존재한다. 이를 해결할 수 있는 방법으로 사전 학습된 언어 모델인 BERT를 활용하는 문장 압축 모델인 Deleter가 제안되었다. Deleter는 BERT를 통해 계산된 perplexity를 활용하여 문장을 압축하기 때문에 문장 압축 규칙과 모델 학습을 위한 데이터셋이 필요하지 않다는 장점이 있다. 하지만 Deleter는 perplexity만을 고려하여 문장을 압축하기 때문에, 문장에 속한 단어들의 언어 정보를 반영하여 문장을 압축하지 못한다. 또한, perplexity 측정을 위한 BERT의 사전 학습에 사용된 데이터가 압축 문장과 거리가 있어, 이를 통해 측정된 perplexity가 잘못된 문장 압축을 유도할 수 있다는 문제점이 있다. 이를 해결하기 위해 본 논문은 언어 정보의 중요도를 수치화하여 perplexity 기반의 문장 점수 계산에 반영하는 방법을 제안한다. 또한 고유명사가 자주 포함되어 있으며, 불필요한 수식어가 생략되는 경우가 많은 뉴스 기사 말뭉치로 BERT를 fine-tuning하여 문장 압축에 적절한 perplexity를 측정할 수 있도록 하였다. 영어 및 한국어 데이터에 대한 성능 평가를 위해 본 논문에서 제안하는 LI-Deleter와 비교 모델의 문장 압축 성능을 비교 실험을 진행하였고, 높은 문장 압축 성능을 보임을 확인하였다.