마졸린씨 궤양에서 발생한 암육종의 증례 보고

문유진,김준혁,이영만,오미혜,조현득,Moon, Yoo-Jin,Kim, Jun-Hyuk,Lee, Young-Man,Oh, Mee-Hye,Cho, Hyun-Deuk 대한성형외과학회 2010 Archives of Plastic Surgery Vol.37 No.1

Purpose: Carcinosarcomas are rare neoplasms in which both malignant epithelial and mesenchymal elements are identified. We have found only twenty one cases of primary cutaneous carcinosarcoma in the English language literature. Therefore it has been difficult to diagnosis because its unclear etiology and low frequency. Methods: A 31-year-old young man with a protruding mass on his ankle dorsum was examined. The tumor was $7{\times}6{\times}3\;cm$ sized and arose from a burn scar. The mass was wide excised and applied split thickness skin graft. Characteristic pathologic finding was a mixture of squamous cell carcinoma and malignant fibrous histiocytoma. Results: Three months after the operation, the patient died of multiple metastasis to the liver, lung and finally of sepsis despite adjuvant chemotherapy and adjuvant radiotherapy. Conclusion: If a metastatic cutaneous carcinosarcoma is diagnosed, wide excision is required. There should be more aggressive management to minimize the risk of recurrence. Further research into the etiology and pathophysiology of the disease and a more careful differential diagnosis may allow improvement in treatment.

공공 빅데이터를 활용한 자동차 사고유형 분석 시스템

문유진(Yoo-Jin Moon),이건우(Gunwoo Lee),김태호(Taeho Kim),전현진(Hyunjin Jun),도송이(Songi Do) 한국컴퓨터정보학회 2017 한국컴퓨터정보학회 학술발표논문집 Vol.25 No.1

Implementation of SENKOV System: A Knowledge Base for Semantic Analysis

문유진,Moon, Yoo-Jin 한국경영정보학회 2000 Information systems review Vol.2 No.2

The paper presents methodology and techniques for design and implementation of the SENKOV System based on the validation of set membership and dictionaries. And it performs verb concept classification available for establishing the selectional restriction relationships among adverbs and verbs. The paper is important in that it has made the first attempt at classifying Korean verb concepts for the semantic analysis. We select about 600 Korean verbs which are commonly used in the daily life, and implements the SENKOV System. According to results of the experiments, SENKOV has 44 top nodes and depth of average 2.35, and that it can be utilized to classify Korean verb concept for the selectional restrictions among adverbs and verbs.

Multilingual Product Retrieval Agent through Semantic Web and Semantic Networks

문유진(Yoo-Jin Moon) 한국지능정보시스템학회 2004 지능정보연구 Vol.10 No.2

상품검색은 고객들이 전자상거래의 접촉을 시작하는 인터페이스로서 매우 중요한 프로세스이다. 또한 전자상거래는 고객들에게 검색 시 쉽게 접근할 수 있는 프로세스를 제공하여야 한다. 특히 World W1de Web 에서 상품정보는 광범위한 고객들이 신속하게 팽창하는 정보를 추적하기 위해서 통합과 표준화가 이뤄져야 한다. 상품 카탈로그 (catalogue) 에 대한 국제 표준화가 다양한 분야와 업종에서 구축되어져 왔는데, 요즈음은 UNSPSC((Universal Standard Poducts and Services Classification) 코드로의 수렴에 대한 논의가 활발해지고 있다. 이 표준을 채택하여 이 논문은 다국어상품검색 에이전트의 아키텍쳐 (architecture) 를 설계한다. 이 아키텍쳐는 중앙 등록기 모델의 상품 카탈로그 관리를 기반으로 하여 분산처리의 update 프로세스를 채택한다. 또한 이 아키텍쳐는 구매자 관점과 공급자 관점을 모두 고려한다. 상품정보의 일관성과 버전 관리는 UNSPSC 코드 시스템에 의하여 제어된다. 고객이 사용하기 편리하도록 표준화에 포함되어 져 있지 않은 상품명과 다국어 상품명은 Semantic Network, 시소러스 (thesaurus) 와 Semantic Web 의 상품명 온톨로지 둥을 활용하여 해결한다. 이를 위한 알고리즘들을 설계하고 또한 구현한다.<br/> This paper presents a method for the multilingual product retrieval agent through XML and the semantic networks in e-commerce. Retrieval for products is an important process, since it represents interfaces of the customer contact to the e-commerce. Keyword-based retrieval is efficient as long as the product information is structured and organized. But when the product information is expressed across many online shopping malls, especially when it is expressed in different languages with cultural backgrounds, buyers' product retrieval needs language translation with ambiguities resolved in a specific context. This paper presents a RDF modeling case that resolves semantic problems in the representation of product information and across the boundaries of language domains. With adoption of UNSPSC code system, this paper designs and implements an architecture for the multilingual product retrieval agents. The architecture is based on the central repository model of product catalog management with distributed updating processes. It also includes the perspectives of buyers and suppliers. And the consistency and version management of product information are controlled by UNSPSC code system. The multilingual product names are resolved by semantic networks, thesaurus and ontology dictionary for product names.<br/>

한영기계번역에서 개념기반의 동사 번역

문유진(Yoo-Jin Moon),김영택(Yung-Taek Kim) 한국정보과학회 1995 정보과학회논문지 Vol.22 No.8

The paper presents the method for concept-based word-sense disambiguation using a collocation dictionary and WordNet to solve the verb translation problem in the KEMT system. The algorithm for verbs in collocation translation refers to the collocation dictionary to find translated English words for Korean verbs. If it fails, it refers to the collocation dictionary once more to find the conceptually close sense of the input Korean verb, refers to WordNet to calculate word distances between the input logical constraints and logical constraints in the collocation dictionary, and selects the translated verb sense with the minimum word distance. 한영기계번역에서 동사의 번역 문제를 해결하는 방안으로, 이 논문에서는 연어사전과 Word-Net을 이용한 개념기반의 다의어 해결 알고리즘을 제시한다. 연어번역 단계에서 사용되는 이 동사번역 알고리즘은, 먼저 연어사전을 참고하여 동사번역어를 찾아보고, 실패하면 연어사전에 있는 명사와 번역해야 할 동사 규제어와의 단어 거리를 WordNet을 사용하여 계산한다. 계산 결과 가장 가까운 명사와 연어로 쓰인 동사를, 번역해야 할 동사와 개념상 가장 가깝다고 인식하여 이 알고리즘은 동사 번역어로 채택한다.

정보 검색을 위한 숫자의 해석에 관한 구문적·의미적 판별 기법

문유진(Yoo-Jin Moon) 한국컴퓨터정보학회 2009 韓國컴퓨터情報學會論文誌 Vol.14 No.8

월드 와이드 웹의 정보 검색에서 산출되어지는 수많은 정보를 효율적으로 검색하기 위해서 자연어 정보처리가 필수적이다. 이 논문은 텍스트에서 숫자의 의미 파악을 위한 판별기법을 제안한 것이다. 숫자 의미 판별기법은 챠트 파싱 기법과 함께 문맥자유 문법을 활용하여 숫자 스트링과 연관된 접사를 해석하였으며, N-그램 기반의 단어에 의거하여 조직화된 의미 파악을 하도록 설계되었다. 그리고 POS 태거를 사용하여 트라이그램 단어의 제한조건이 자동 인식되도록 시스템을 구성하여, 점진적으로 효율적인 숫자의 의미 파악을 하도록 하였다. 이 논문에서 제안한 숫자 해석 시스템을 실험한 결과, 빈도수 비례 방법은 86.3%의 정확률을 나타냈고 조건수 비례 방법은 82.8%의 정확률을 나타냈다. Natural language processing is necessary in order to efficiently perform filtering tremendous information produced in information retrieval of world wide web. This paper suggested an algorithm for meaning of numerals in the text. The algorithm for meaning of numerals utilized context-free grammars with the chart parsing technique, interpreted affixes connected with the numerals and was designed to disambiguate their meanings systematically supported by the n-gram based words. And the algorithm was designed to use POS (part-of-speech) taggers, to automatically recognize restriction conditions of trigram words, and to gradually disambiguate the meaning of the numerals. This research performed experiment for the suggested system of the numeral interpretation. The result showed that the frequency-proportional method recognized the numerals with 86.3% accuracy and the condition-proportional method with 82.8% accuracy.

한국어 명사를 위한 WordNet의 설계와 구현

문유진(Yoo-Jin Moon) 한국정보과학회 1996 정보과학회 컴퓨팅의 실제 논문지 Vol.2 No.4

이 논문은 의미론적 어휘개념에 기반하여 한국어 명사 WordNet을 설계하고 구축하였다. 한국어 명사 WordNet의 설계에 있어서 중요한 관건은 기본 골격인 어휘개념을 표현하는 형식과 계층구조 관계 설정이다. 어휘개념을 차별화 이론을 채택하여 영어 WordNet의 동의어 집합과 한국어 명사에 알맞은 어휘개념을 만들어 표현하였고 계층구조는 이 노드들 간의 상하위개념 관계로 표현하였다. 이 시스템을 구축하는 데 있어서 어휘개념의 pruning시 어휘개념의 선택이 어렵고 또한 시간도 많이 걸린다. 이와같이 구축한 한국어 명사 WordNet을 실제 응용 시스템인 한영기계번역 시스템의 동사 번역에적용한 결과, 실용성이 있음이 증명되었다. 이 논문은 한국어 Isa 계층구조의 어휘개념을 단어 한 개가 아닌 동의어 집합으로 표현하였다는 데에 의의가 있다. The paper designs and implements WordNet for Korean nouns based on the analysis of semantic word concept. In the design of WordNet for Korean nouns, it is the most important task how to represent the nodes of word concept and to establish the relation of their hierarchies. WordNet for Korean nouns adopts the differential theory, and represents the word concept with synonym sets of English WordNet and those of Korean nouns. And it represents the relation of their hierarchies with hypernymous relations among the word concepts. It has been proved that WordNet for Korean nouns is a practical tool when applied to verb translation in the real Korean-English Machine Translation System. In the implementation of the system there are difficulties in pruning word concepts for Korean nouns. To solve these difficulties, we need common senses and word concept of linguists. The paper is significant in that Isa hierarchies for Korean nouns have been implemented with word concepts which arc represented by synonym sets, not by a word.

SNS 감정 분석을 이용한 선거 후보자 순위 예측 시스템

문유진(Yoo-Jin Moon),이한수(Hansoo Lee),박혁(Hyuk Park),이재영(Jaeyoung Lee),김선국(Sunguk Kim) 한국컴퓨터정보학회 2017 한국컴퓨터정보학회 학술발표논문집 Vol.25 No.1

동사의 의미분석처리를 위한 SENKOV 시스템의 설계와 구현

문유진 ( Yoo Jin Moon ) 한국정보처리학회 2000 정보처리학회논문지 Vol.7 No.4

Human-compute interface (HCl) should be designed with ease and flexibility for users for providing convenience and friendliness to users. The natural language processing is one of the aspects of HCl. This paper presents the method of design and implementation of SENKOV( Semantic Networks for Korean Verbs) System, which deals with isa hierarchies of Korean verbs for the natural language processing. The system``s architecture is based on the differential theory and Levin verb classes. This paper selects about 600 Korean verbs which are commonly used in the daily life, and implements the SENKOV System. The experiments show that SENKOV has 44 top nodes and depth of about 2.35. In addition this paper applied the SENKOV System to co-occurrence constraint relationship among a adverbs and verbs, and proves the validity of the system. This paper is important in that it has made the first trial to classify Korean verb concept for HCl.

기계번역에서 동사 모호성 해결에 관한 하이브리드 기법

문유진(Moon Yoo Jin),마르타 파머(Martha Palmer) 한국정보처리학회 1998 정보처리학회논문지 Vol.5 No.3

The paper presents a hybrid method for disambiguation of the verb meaning in the machine translation. The presented verb translation algorithm is to perform the concept-based method and the statistics-base method simultaneously. It uses a collocation dictionary, WordNet and the statistical information extracted from corpus. In the transfer phase of the machine translation, it tries to find the target word of the source verb. If it fails, it refers to WordNet to try to find it by calculating word similarities between the logical constraints of the source sentence and those in the collocation dictionary. At the same time, it refers to the statistical information extracted from corpus to try to find it by calculating co-occurrence similarity knowledge. The experimental result shows that the algorithm performs more accurate verb translation than the other algorithms and improves accuracy of the verb translation by 24.8% compared to the collocation-based method.