• International Journal of Contents
• /
• v.12 no.4
• /
• pp.53-61
• /
• 2016

Although extensively developed, optical music recognition systems have mostly focused on musical symbols (notes, rests, etc.), while disregarding the chord symbols. The process becomes difficult when the images are distorted or slurred, although this can be resolved using optical character recognition systems. Moreover, the appearance of outliers (lyrics, dynamics, etc.) increases the complexity of the chord recognition. Therefore, we propose a new approach addressing these issues. After binarization, un-distortion, and stave and lyric removal of a musical image, a rule-based method is applied to detect the potential regions of chord symbols. Next, a lexicon-driven approach is used to optimally and simultaneously separate and recognize characters. The score that is returned from the recognition process is used to detect the outliers. The effectiveness of our system is demonstrated through impressive accuracy of experimental results on two datasets having a variety of resolutions.

• Journal of the Korean housing association
• /
• v.17 no.5
• /
• pp.27-37
• /
• 2006

This paper analyzed statistically two corpora that were constructed from the texts about house designs written by Korean architects and PA Awards architects. The main results are as follows; (1) The numbers of words in Korean house-design corpus were 9,352 and those of words in PA Awards house design corpus were 2,379. The former were 18.7% and the latter 4.8% of about 50,000 words regarded as the rest using scale in actual life. (2) When the architects described their house designs, the lexicon-concentration phenomenon was pervasive in both groups. Therefore, we can infer that the high-frequency lexicons are very important in house design. (3) The architects' behaviour patterns of using the house-design lexicons, went by rules according to the word frequency order. The tendency formulas of them had the $R^{2}$ values which were more than 90%. (4) In Korean house design corpus, the high frequency lexicons were '공간', '층', '주택', '집', '대지', '거실', and '실'. In PA awards house design corpus, they were 'house','room','space','living','wall','level' and 'area'. From these results, We can tell that 'space' is the highest frequency word in house design of the two groups, and that '대지 ' and 'wall' are the words that reveal well the differences between the two groups.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.18 no.5
• /
• pp.15-21
• /
• 1981

This paper deals with the syntactic analysis algorithms of Korean sentence and system for machine translation. The parts of speech and constituients are syntactically analized at unified view-points and then an effective classification algorithm is proposed. The constituients which are applied an inverse movement transformation algorithm are processed with the concept of attribute. Syntactic analysis system is constructed to generate parsing table including the deep structure of sentence by lexicon proper to the combinational property of Korean and breadth-first searching method. The results obtained from the system program are shown as the parsing table of source sentences.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.158-162
• /
• 2007

Anomia, word finding difficulty, is one of the most common feature in aphasia. Previous studies support that the process of picture naming consists of three stages, in the order of the object recognition, semantic, and phonological output stages. Anomic patients have many symptoms and it means that anomia can be sub-divided into several symptom groups. Our anomia assessment battery consists of several parts: (1) picture naming set, (2) picture-word matching task, (3) lexical decision task for mental lexicon damage, (4) naming task for phonological lexicon damage, and (5) semantic decision task. Pictures and words were selected on the basis of usage frequency, semantic category, and word length. We administered this anomia evaluation battery to many anomic aphasics and we subdivided patients into several groups. We hope that our anomia evaluation set is useful and helpful for evaluation anomic aphasics

• Journal of Information Management
• /
• v.32 no.2
• /
• pp.26-39
• /
• 2001

Various controlled vocabularies such as thesaurus and classification used for effective information retrieval contain different terms in expressing the same concept or meaning. National Library of Medicine has developed the Unified Medical Language System(UMLS) to solve the problems of information retrieval and integration resulted from the difference of concepts between different sources. The UMLS development was initiated in 1982 as a long-term project, and the 2001 edition of the UMLS consists of three parts : Metathesaurus, Semantic Network, and SPECIALIST Lexicon. This paper reviews background and structure of the UMLS including applications in PubMed, NLM Gateway.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.27-32
• /
• 2013

본 논문은 잘 알려지지 않은 언어 쌍에 대해서 병렬말뭉치(parallel corpus)로부터 자동으로 이중언어 사전을 추출하는 방법을 제안하였다. 이 방법은 중간언어(pivot language)를 매개로 하고 문맥 벡터를 생성하기 위해 공개된 단어 정렬 도구인 Anymalign을 사용하였다. 그 결과로 초기사전(seed dictionary)을 사용한 문맥벡터의 번역 과정이 필요 없으며 통계적 방법의 약점인 낮은 빈도수를 가지는 어휘에 대한 번역 정확도를 높였다. 또한 문맥벡터의 요소 값으로 특정 임계값 이상을 가지는 양방향 번역 확률 정보를 사용하여 상위 5위 이내의 번역 정확도를 크게 높였다. 본 논문은 두 개의 서로 다른 언어 쌍 한국어-스페인어 그리고 한국어-프랑스어 양방향에 대해서 각각 이중언어 사전을 추출하는 실험을 하였다. 높은 빈도수를 가지는 어휘에 대한 번역 정확도는 이전 연구에서 보인 실험 결과에 비해 최소 3.41% 최대 67.91%의 성능 향상을 보였고 낮은 빈도수를 가지는 어휘에 대한 번역 정확도는 최소 5.06%, 최대 990%의 성능 향상을 보였다.

• Lingua Humanitatis
• /
• v.1 no.2
• /
• pp.107-121
• /
• 2001

This paper examines the way in which the idea of language has been introduced in architectural discourse since the late 1960s. The paper reviews the works of Robert Venturi, Charles Jencks, Peter Eisenman, Alan Colquhoun, and Mario Gandelsonas, which explore the analogy between linguistic and architectural form. All of the writers above are responsive to each other's theoretical positions, sometimes implicitly and sometimes explicitly. A system of signs can be approached by asking how the lexicon and syntax are proportioned. The same question may be posed to architecture: can architecture be understood as a lexicon or as a relational structure, such as language is\ulcorner Two perspectives are presented by architectural theorists. The first advocated by Venturi and Jencks posit architectural form as a problem of signs. The problem with this perspective is that, it reduces architecture into popularized iconography in favor of the representational aspects of architectural form. The second perspective, developed by Eisenman, explores the possibility of finding new formal constructs in the abstract relationship of formal properties. Eisenman's theory, however, has its own problems for, in highlighting syntactic structure, it minimizes the distinction between the perceptual and the pragmatic dimensions. Yet both perspectives address crucial problems of contemporary architecture and expand architectural discourse into the broader realm of humanistic studies.

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.41-48
• /
• 2005

This paper presents the development of a morphological processor for the Mongolian language, based on the two-level morphological model which was introduced by Koskenniemi. The aim of the study is to provide Mongolian syntactic parsers with more effective information on word structure of Mongolian words. First hand written rules that are the core of this model are compiled into finite-state transducers by a rule tool. Output of the compiler was edited to clarity by hand whenever necessary. The rules file and lexicon presented in the paper describe the morphology of Mongolian nouns, adjectives and verbs. Although the rules illustrated are not sufficient for accounting all the processes of Mongolian lexical phonology, other necessary rules can be easily added when new words are supplemented to the lexicon file. The theoretical consideration of the paper is concluded in representation of the morphological phenomena of Mongolian by the general, language-independent framework of the two-level morphological model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.802-805
• /
• 2015

본 논문은 인공신경망(artificial neural network)의 한 종류인 자기조직화 지도(self-organizing map)를 이용하여 비교말뭉치(comparable corpora)로부터 이중언어사전(bilingual lexicon)을 자동으로 구축하는 방법에 대하여 기술한다. 일반적으로 우리가 대상으로 하는 언어 쌍마다 말뭉치 혹은 초기사전과 같은 언어 자원을 수집하고 그것을 필요에 맞게 가공하는 것은 매우 어려운 일이다. 이런 관점에서 볼 때, 비지도학습(unsupervised learning) 방법 중 하나인 자기조직화 지도를 이용하여 사전을 구축하면 다른 방법에 비해 적은 노력으로도 더 높은 성능을 얻을 수 있다. 본 논문에서는 한국어와 불어에 대하여 실험을 하였고, 그 결과 적은 양의 초기사전으로도 주목할 만한 정확도를 얻을 수 있었다. 향후 연구로는 학습 파라미터에 대해 좀 더 다양한 실험을 하고, 다른 언어 쌍으로의 적용 및 기존의 평가사전을 확장하여 더 많은 경우에 대해 실험하는 것을 들 수 있다.

• Cross-Cultural Studies
• /
• v.23
• /
• pp.383-418
• /
• 2011

The purpose of this research is to find out how the Chinese Bronze Epigraphy has developed and how it has influenced the Chinese Academic field. The Chinese Bronze Epigraphy started from the Han dynasty, however it didn't reach the professional academic stage. After the Song Dynasty it started to be studied in full scale. Therefore, it is reasonable to see that the start of the study of bronze was from the Song dynasty. In the Qing Dynasty, the study in Epigraphy was extended on again. ShuoWenJieZi that was written by XuShen in the Han Dynasty. KaoGuTuShiWen that was written by $L{\check{u}}DaLin$ in the Song Dynasty. ShuoWenGuZhouBu that was written by WuDaCheng in the Qing Dynasty. JinWenBian that was written by RongGeng in the Republican era. This thesis examines the contents of ShuoWenGuZhouBu and JinWenBian and then synthetically compares and analyzes them. The conclusion of this study is as follows. It cannot be denied that ShuoWenJieZi and KaoGuTuShiWen significantly affected the birth of ShuoWenGuZhouBu and JinWenBian.