• 한국융합학회논문지
• /
• 제12권5호
• /
• pp.23-29
• /
• 2021

최근 딥러닝 기반 자연언어처리 연구들은 다양한 출처의 대용량 데이터들을 함께 학습하여 성능을 올리고자 하는 연구들을 진행하고 있다. 그러나 다양한 출처의 데이터를 하나로 합쳐서 학습시키는 방법론은 성능 향상을 막게 될 가능성이 존재한다. 기계번역의 경우 병렬말뭉치 간의 번역투(의역, 직역), 어체(구어체, 문어체, 격식체 등), 도메인 등의 차이로 인하여 데이터 편차가 발생하게 되는데 이러한 말뭉치들을 하나로 합쳐서 학습을 시키게 되면 성능의 악영향을 미칠 수 있다. 이에 본 논문은 기계번역에서 병렬말뭉치 간의 균형성을 고려한 Corpus Weight Balance (CWB) 학습 방법론을 제안한다. 실험결과 말뭉치 간의 균형성을 고려한 모델이 그렇지 않은 모델보다 더 좋은 성능을 보였다. 더불어 단일 말뭉치로도 고품질의 병렬 말뭉치를 구축할 수 있는 휴먼번역 시장과의 상생이 가능한 말뭉치 구축 프로세스를 추가로 제안한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1106-1110
• /
• 2004

A human sign language is generally composed of both static and dynamic gestures. Each gesture is represented by a hand shape, its position, and hand movement (for a dynamic gesture). One of the problems found in automated sign language translation is on segmenting a hand movement that is part of a transitional movement from one hand gesture to another. This transitional gesture conveys no meaning, but serves as a connecting period between two consecutive gestures. Based on the observation that many dynamic gestures as appeared in Thai sign language dictionary are of quasi-periodic nature, a method was developed to differentiate between a (meaningful) dynamic gesture and a transitional movement. However, there are some meaningful dynamic gestures that are of non-periodic nature. Those gestures cannot be distinguished from a transitional movement by using the signal quasi-periodicity. This paper proposes a hybrid method using a combination of the periodicity-based gesture segmentation method with a HMM-based gesture classifier. The HMM classifier is used here to detect dynamic signs of non-periodic nature. Combined with the periodic-based gesture segmentation method, this hybrid scheme can be used to identify segments of a transitional movement. In addition, due to the use of quasi-periodic nature of many dynamic sign gestures, dimensionality of the HMM part of the proposed method is significantly reduced, resulting in computational saving as compared with a standard HMM-based method. Through experiment with real measurement, the proposed method's recognition performance is reported.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.427-436
• /
• 2021

The article reveals and theoretically substantiates the trends of foreign language teachers' professional training in universities of Ukraine in terms of European integration, which are systematized in three areas: macro-level (system of education), meso-level (universities) and micro-level (subjects of educational process). The article aims to substantiate the trends of foreign language teacher training in the context of European integration and the main directions of creative use of constructive ideas of European experience in the innovative development of education. The article lights up the system for improving foreign language teacher training in universities, which is based on updated goals, content and approaches to the implementation of basic concepts, principles and features of teacher training in European experience, enable us to improve the quality of teacher training, its competitiveness in the European labor market. In the article developed the conceptual model of strategic development of the university in the conditions of European integration. It is emphasized that information technologies provide great opportunities for the development of professional skills and intellectual potential of future professionals. At present, the computerization of the educational process in higher education institutions is considered as one of the first and most promising areas for improving the quality of education. The article offered directions of internationalization of educational activity of university in the conditions of European integration. Diagnostic tools for the development of the university in terms of integration into the European educational space, individual rating and ranking of structural units of the university have been developed; main directions of activity of the laboratory of the skill of the teacher of higher school and methodical recommendations on the creation and the organization of work of scientific laboratories.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.284-287
• /
• 2003

In recent years, most of the researches on pattern recognition are for medical diagnosis or for characters recognition. In fact its applications are very wide. In this paper, the pattern recognition is employed by linguistic translation, i.e. the output of Pattern Recognition is translated into another language. In this paper, it focuses on several fields: (1) System overview-explicate the functions of each part individually; (2) Criteria on the system-discuss the difficulties in each part; (3) System implementation-discuss how to design the approaches for constructing the system. Furthermore, intelligent approaches are considered be use on the system in different parts. They are discussed in the late paper, and also we concentrate on user interface, which can make a serious of processes in order, and easy control-just only pressing a few buttons. It is a new and creative attempt in digital system.

• 한국문헌정보학회지
• /
• 제18권
• /
• pp.157-212
• /
• 1990

Translation has attained an important role in transmission and maintenance of human culture. As the world gets closer translation is regarded as one of the most useful means to carry knowledge and information through the language barrier. Translations of literary works in particular have been regarded as one of the most valuable means of helping people to understand and cooperate with one another in the interest of world peace. Korea has maintained a very close relationship with the United States of America since she first opened her door to the States in 1882. No one can deny that American has had a strong influence on Korean culture, politics, economics and education through the long close relationship between two countries. This study has been carried to find out how many and what American literary works have been introduced into Korea through translation from 1882 to 1982.

• Journal of Information Technology Applications and Management
• /
• 제9권2호
• /
• pp.71-80
• /
• 2002

Automatic language translation has greatly advanced due to the increased user needs and Information retrieval in WWW. This paper utilizes the integrated knowledge bases of noun and verb networks for automatic translation of ambiguous words in the Korean sentences, through the selectional restriction relation in the sentences. And this paper presents the method to verify validity of Korean noun semantic networks that are used for the construction of the selectional restriction relation by applying the networks to the syntactic and semantic properties Integration of Korean Noun Networks into the SENKOV system will provide the accurate and efficient knowledge bases for the semantic analysis of Korean NLP.

• Genomics & Informatics
• /
• 제19권3호
• /
• pp.26.1-26.3
• /
• 2021

Previous approaches to create a controlled vocabulary for Japanese have resorted to existing bilingual dictionary and transformation rules to allow such mappings. However, given the possible new terms introduced due to coronavirus disease 2019 (COVID-19) and the emphasis on respiratory and infection-related terms, coverage might not be guaranteed. We propose creating a Japanese bilingual controlled vocabulary based on MeSH terms assigned to COVID-19 related publications in this work. For such, we resorted to manual curation of several bilingual dictionaries and a computational approach based on machine translation of sentences containing such terms and the ranking of possible translations for the individual terms by mutual information. Our results show that we achieved nearly 99% occurrence coverage in LitCovid, while our computational approach presented average accuracy of 63.33% for all terms, and 84.51% for drugs and chemicals.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2003년도 제15회 한글 및 한국어 정보처리 학술대회
• /
• pp.235-240
• /
• 2003

본 논문에서는 영한 자동번역 시스템에 한국어 스타일 생성 패턴을 적용함으로써 영한 번역 품질을 향상하고자 하는 것이 목표이다. 이러한 목표는 기존의 원문에 대한 번역문의 정보 전달 정확성을 측정하는 1차원적인 번역률 평가 방법에서 벗어나 번역문의 정보 정확성뿐만 아니라 자연스러움도 평가할 수 있는 2차원적인 번역률 평가방법으로써 정확성과 스타일을 동시에 평가하는 방법을 제안한다. 2차원적인 번역률 평가 방법에 따라 스타일 생성 패턴이 적용되기 전과 적용된 후의 평가 결과는 100문자의 샘플문을 대상으로 하였을 때, 스타일 생성 패턴에 의해서만 0.5%의 번역률이 향상되는 것을 관찰하였다. 본 논문에서의 스타일 생성 패턴은 단순히 언어간 스타일 차이만 적용한 것이며 향후에는 신문, 일기예보, 기술 매뉴얼과 같은 특정 그룹을 위한 스타일 생성 패턴을 적용할 계획이다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.678-681
• /
• 2018

Dependency parsing is an important task in natural language processing whose results are used in many downstream tasks such as machine translation, information retrieval, relation extraction, question answering and many others. Most of the dependency parsing literature focuses on using end-to-end and sequence-to-sequence neural architectures as the core of the system. One such system, namely Biaffine dependency parser is explored in the current paper for effective dependency parsing of Korean language.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2014년도 제26회 한글 및 한국어 정보처리 학술대회
• /
• pp.173-174
• /
• 2014

본 연구는 현재 개발 진행 중인 다국어 자동통번역시스템에서 발생하는 한국어 과거시제 선어말어미 '-었'의 생성문제를 다루었다. 한국어 과거시제 선어말 어미는 영어와 독일어의 경우에는 대부분 단순과거형으로 생성될 수 있으나, 프랑스어의 경우에는 복합과거의 형식과 반과거의 형식 중 하나를 선택해야 하는 문제가 발생한다. 본 연구에서는 이러한 문제의 해결을 위해 한-프랑스어 코퍼스 분석을 통해 복합과거와 반과거의 올바른 생성을 위한 네 가지의 자질을 선정하였고, 이에 SVM 알고리즘을 적용한 분류기를 구현하였다. 현재까지의 실험결과는 84.45%의 정확률이며 현재 성능개선을 위한 연구가 계속 진행 중이다.