• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.101-106
• /
• 1989

음성 및 문자를 통한 컴퓨터와의 정보 교환을 위한 통합 사용자 인터페이스 (Intelligent Man- Machine interface) 시스템의 일환으로 한국어 단모음의 인식을 위한 시스템을 인공 신경망 모델을 사용하여 구현하였으며 인식시스템의 상위 접속부에 필요한 단어 인식 모듈에 있어서의 인지 실험도 행하였다. 모음인식의 입력으로는 제1, 제2, 제3 포르만트가 사용되었으며 실험대상은 한국어의 [아, 어, 오, 우, 으, 이, 애, 에]의 8 개의 단모음으로 하였다. 사용한 인공 신경망 모델은 Multilayer Perceptron 이며, 학습 규칙은 Generalized Delta Rule 이다. 1 인의 남성 화자에 대하여 약 94%의 인식율을 나타내었다. 그리고 음성 인식시의 인지 현상 실험을 위하여 약 20개의 단어를 인공신경망의 어휘레벨에 저장하여 음성의 왜곡, 인지시의 lexical 영향, categorical percetion등을 실험하였다. 이때의 인공 신경망 모델은 Interactive Activation and Competition Model을 사용하였으며, 음성 입력으로는 가상의 음성 피쳐 데이타를 사용하였다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.5
• /
• pp.683-693
• /
• 2012

Recently, statistical machine translation (SMT) has received many attention with ease of its implementation and maintenance. The goal of our works is to build bidirectional Korean-Japanese SMT system by using MOSES [1] system. We use Korean-Japanese bilingual corpus which is aligned per sentence to train the translation model and use a large raw corpus in each language to train each language model. The proposed system shows results comparable to those of a rule-based machine translation system. Most of errors are caused by noises occurred in each processing stage.

• Language and Information
• /
• v.17 no.2
• /
• pp.93-121
• /
• 2013

Identifying the speakers of individual utterances mentioned in textual stories is an important step towards developing applications that involve the use of unique characteristics of speakers in stories, such as robot storytelling and story-to-scene generation. Despite the usefulness, it is a challenging task because not only human entities but also animals and even inanimate objects can become speakers especially in fairytales so that the number of candidates is much more than that in other types of text. In addition, since the action of speaking is not always mentioned explicitly, it is necessary to infer the speaker from the implicitly mentioned speaking behaviors such as appearances or emotional expressions. In this paper, we investigate a method to exploit linguistic clues to identify the speakers of utterances from textual fairytale stories in Korean, especially in order to handle such challenging issues. Compared with the previous work, the present work takes into account additional linguistic features such as vocative roles and pairs of conversation participants, and proposes the use of discourse-level turn-taking behaviors between speakers to further reduce the number of possible candidate speakers. We describe a simple rule-based method to choose a speaker from candidates based on such linguistic features and turn-taking behaviors.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.636-644
• /
• 2016

Annotated Corpus is important to understand natural language using machine learning method. In this paper, we propose a new method to automate error reduction of annotated corpora. We use the Ripple-Down Rules(RDR) for reducing errors and Kernel to extend RDR for NLP. We applied our system to the Korean Wikipedia and blog corpus errors to find the annotated corpora error type. Experimental results with various views from the Korean Wikipedia and blog are reported to evaluate the effectiveness and efficiency of our proposed approach. The proposed approach can be used to reduce errors of large corpora.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.4
• /
• pp.108-114
• /
• 2002

After automatic translation system for hangul's romanization based on the World Wide Web converting korean-word, sentence, document to Transliteration letters by applying algorithm based phonological principles. even though a user do not know the basic principles of the usage of Korean-to-Romanization notations, It refers to corresponding character table that has been currently adopted the authority's standard proposition for Korean-to-Romanization notation rule concurrently, add to make possible to convert a machinized code as well. It provides font for toggling Korean-English mode, insert-edit mode by assigning ASCII codes and Unicode are hardly used to them. This program could be made in C++ progamming language and Unified Modeling Language to implement various font. font-expanding and condensing. alternative printing.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.584-588
• /
• 1997

Lots of forginfs used in automobile and aerospce industries are made in hot or cold working conditions, depending on the size and shape of a product. Usually the die design for new items has been first made on the basis of experiences and many know-hows accumulated in the company and then slightly modified through trial and error method to get the desired forgings without defects. Most of drawings at the die design stage have been manually drawn, butrecently some of forging companies have begun to apply a computer-aided drafting technique to the die design for reducing drafting time as well as repeatedly utilizing standardized parts form registerd data base. In this paper the automated die design technique for forward extrusion of axisymmetric forgings is developed by using AutoLISP language. For this study the representative die system is determined form the investigation of several types of forging dies being currently employed in the metal forming field and the design rules for cold extrusion die are summarized and programmed on a personal computer. A few design examples of forward extrusion die are given and discusses.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.101-108
• /
• 2005

Apraxia of phonation (AOP) has often been described as a feature of apraxia of speech or of severe non-fluent type of aphasia. Pure AOP is rare and, to our knowledge, only two cases have been reported. Brain lesion sites of the reported cases were not those sites known to be responsible for apraxia of speech. This study presents a case of AOP which resulted from the secondary stroke in the left corona radiata immediately following the first stroke in the left temporoparietal lobe. A 61-year old right-handed man shwoed a global type of aphasia after the first cerebral infarction, but was able to generate spontaneously some short fragments of speech. On the day after the first infarction, he suffered from the secondary infarction, leaving him a complete loss of voluntary phonation. He did not showed any significant change in language functions. Several occurrences of involuntary phonation were observed upon laughing or crying. He was also able to cough unintentionally. A vidoe-stroboscopic examination failed to reveal any evidence of structural and functional impairment in larynx. Although this case is not of pure form of AOP, AOP appeared after the secondary stroke without significant changes of language impairment since the first stroke. Therefore, AOP may be a consequence of the brain lesion from the secondary stroke even though we cannot rule out the possibility of an additive effect of the secondary to the first stroke.

• The Journal of Information Technology
• /
• v.2 no.2
• /
• pp.35-49
• /
• 1999

This papar describes an design and implementation of a rule builder, named SGML DTD(Document Type Definition) Editor conforming to ISO 8879(SGML : Standard Generalized Markup Language). SGML DTD define types of logical structure in documents and it is very hard to managing, operating with general common text editors because of it's complex structures. Therefore, We studied DTD automatic editor and production system, prototype system, direct operations on graphic trees in the environment of windows. It's easy to handle with general users. So, We analyzed the structures of document, and studied about SGML documents operation models. And also described logical structures by tree on Windows.

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.139-144
• /
• 2005

When a Japanese learner in Korea tries to find Japanese dictionary, he must know the pronunciation of the target word. But it's not easy to know the pronunciation of target word from Japanese sentence. Because most of general Japanese sentence shows only HanJa(Chinese character) instead of Kana(Japanese alphabet). If the Japanese learner knows the Korean traditional pronunciation of the target word, he can input the word to electronic Japanese dictionary with the Korean pronunciation. For this solution, the dictionary service provider must convert the Japanese word to Korean pronunciation, in advance. After setting of the conversions as a additional searching process, we can find the target word through Korean pronunciation of the Japanese HanJa, This process is possible for the three reasons below, 1. Korean, Japanese and Chinese are using the nearly same HanJa. The difference is small. 2. Most Japanese learner in Korea, knows the Korean pronunciation of the HanJa. 3. The Korean pronunciation of the HanJa is nearly unique, a HanJa has a Korean pronunciation, generally.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.991-998
• /
• 2002

With the advent of XML and database languages armed with the object-oriented concept and deductive logic, the problem of efficient query processing for them has become a major issue. We describe a way of processing semi-structured XML data through an implementation of a Deductive and Object-oriented Database (DOODB) language with the explanation of query processing. We have shown how to convert an XML data model to a DOODB data model. We have then presented an efficient query processing method based on Connection Graph Resolution. We also present a knowledge-based query processing method that uses the homomorphism of objects in the database and the associative rule of substitutions.