• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.508-524
• /
• 2021

Innovative translation circumstances encouraged by scientific technique have become an element that increases realization and possibility of expanding sign language translation and Korean sign language translation is facing a new challenge and opportunity. This study raises following questions and search for answers. First, when and how did Korean sign language translation appear in the course of the historical changes in Korean sign language? Second, what is the form and characteristic of translation produced as a result of Korean sign language translation? Third, what is the present condition and prospect of Korean sign language translation? Accordingly, this study examined how Korean sign language translation was formed historically and the form and characteristics of Korean sign language translation using integrated literature review method. As a result of the study, first, the form and characteristics of Korean sign language translation classified according to the historical transition process into latent phase, formation phase, and expansion phase were revealed. Second, the forms and characteristics of Korean sign language translation according to the Korean sign language corpus project and machine translation were derived. In addition, it apprehends its present condition and proposes its future prospect.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.185-192
• /
• 2019

In the case of a hearing impaired person using sign language, there are many difficulties in communicating with a normal person who does not understand sign language. The sign language translation system is a system that enables communication between the hearing impaired person using sign language and the normal person who does not understand sign language in this situation. Previous studies on sign language translation systems for communication between normal people and hearing impaired people using sign language are classified into two types using video image system and shape input device. However, the existing sign language translation system does not solve such difficulties due to some problems. Existing sign language translation systems have some problems that they do not recognize various sign language expressions of sign language users and require special devices. Therefore, in this paper, a sign language translation system using an artificial neural network is devised to overcome the problems of the existing system.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.313-321
• /
• 1996

본 논문에서는 실용적인 기계번역 시스템을 위하여 다양한 입력 형태에서 나타나는 여러 현상을 전처리하는 기법을 설명한다. 전처리기는 문장 분리, Title 및 나열문 인식, HTML Tag의 처리, 하이픈처리, 숫자 표현 처리, 대소문자의 정규화, 고유명사 인식, 복합단위 인식 등을 수행하여 형태소 분석기의 처리 부담을 줄인다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.504-509
• /
• 2018

Neural machine translation (NMT) has recently achieved the state-of-the-art performance. However, it is reported failing in the word sense disambiguation (WSD) for several popular language pairs. In this paper, we explore the extent to which NMT systems are able to disambiguate the Korean homographs. Homographs, words with different meanings but the same written form, cause the word choice problems for NMT systems. Consistent with the popular language pairs, we discover that NMT systems fail to translate Korean homographs correctly. We provide a Korean word sense disambiguation tool-UTagger to use for improvement of NMT's translation quality. We conducted translation experiments using Korean-English and Korean-Vietnamese language pairs. The experimental results show that UTagger can significantly improve the translation quality of NMT in terms of the BLEU, TER, and DLRATIO evaluation metrics.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.193-200
• /
• 2019

Hearing impaired people are living in a voice culture area, but due to the difficulty of communicating with normal people using sign language, many people experience discomfort in daily life and social life and various disadvantages unlike their desires. Therefore, in this paper, we study a sign language translation system for communication between a normal person and a hearing impaired person using sign language and implement a prototype system for this. Previous studies on sign language translation systems for communication between normal people and hearing impaired people using sign language are classified into two types using video image system and shape input device. However, existing sign language translation systems have some problems that they do not recognize various sign language expressions of sign language users and require special devices. In this paper, we use machine learning method of artificial neural network to recognize various sign language expressions of sign language users. By using generalized smart phone and various video equipment for sign language image recognition, we intend to improve the usability of sign language translation system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.273-281
• /
• 2016

In this paper, we consider the discussion of the breakdown phenomenon of korean language that is displayed in the language of the Internet media, as a technical improvement approach to this, and to provide an automatic translation technology of standard language. The collected through real life surveys and experience and damage case regarding language breakdown phenomena in the FGI (Focussed Group Interview), and presents the results of the analysis, based on the analysis result data, we defined the index of language destroyed (degree of Korean destruction). The limit of the national language break or automatic translation technology standard language marked with translation errors that have to be minimized, the efficiency of the automatic translation technology standard language which may be utilized as a measure to get the maximum, and presented through the Internet media texts 2,480 pieces of analysis. Automatic translation technology of the standard language and was also measured the proposed language destroyed in this paper, we implemented in the form of a REST API using the Java language, was confirmed to work on the Web browser.

• Cross-Cultural Studies
• /
• v.33
• /
• pp.309-330
• /
• 2013

This paper explores the concept of pure language introduced in Walter Benjamin's "The Task of the Translator" and looks at various perspectives on this concept represented in theories of Paul De Man and Gilles Deleuze and a short story of Jorge Luis Borges. According to "The Task of the Translator," pure language is defined as a vessel of which fragments are the original and the translation. Just as fragments are part of a vessel, so the original and the translation are fragments of a greater language, which is pure language. On the other hand, De Man, from a deconstructive criticism, says that pure language does not exist except as a permanent disjunction, which inhabits all languages as such, and that any work is totally fragmented in relation to this pure language and every translation is totally fragmented in relation to the original. While De Man consider pure language incorporeal, Deleuzian interpretation regards it as a virtual object or differenciator in relation to which the two series of the original and the translation coexist and resonate. Finally in Borges's "Pierre Menard, Author of the Quixote" Menard attempt to translate Cervantes's Don Quixote identically in every detail. By showing a case in which the original and the translation are the same, Borges raises a question what would take place in relation to pure language if the original and the translation were identical. In Deleuze, identity and resemblance are the result of a differenciator, but in Borges, identity is a differenciator which produces differences. If we apply this logic to the last paragraph of "The Task of the Translator," we can say the interlinear version of Scriptures, as the prototype or ideal of all translation, in the form of which the original and the translation must be one, is a differenciator, an endless difference-making machine.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.283-287
• /
• 1997

본 논문에서는 당 연구소 주관으로 연구개발정보센터(KORDIC), 서울대와 공동으로 개발중인 한영 기계번역 시스템, '에서로/KE'의 prototype system을 설명한다. 에서로/KE는 KORDIC에서 한국어 형태소 분석기와 Tagger를 개발하고, 서울대에서 한국어 구문해석기와 한영 변환기를 개발하고, SERI에서 영어 구문 생성기와 영어 형태소 생성기를 개발한다. 한국어 Tagger는 HMM에 기반하여 제작되었으며 sample 200문장에 대해 98.9%의 정확률을 보인다. 한국어 구문 해석기는 의존 문법에 기반하여 CYK 알고리즘을 사용하여 제작되었으며 중의성 해결을 위해 29개의 최적 parse 선택 규칙이 구현되어 있다. 한영 변환기는 collocation과 idiom에 기반하여 한영 변환을 수행한다. 영어 구문 생성기는 Tree 변환 언어인 GWL(Grammar Writing Language)를 사용하여 작성되었으며, 영어 형태소 생성기는 최종적으로 자연스러운 영어 표층문을 생성한다. 에서로/KE는 현재 1차년도 Prototype system이 Unix 환경에서 구현되어 있으며, 현재 각 모듈별 성능 개선과 대량 사전 구축을 통해 상용화될 예정이다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.105-114
• /
• 2007

This paper addresses a method for customizing an English-to-Korean machine translation system from general domain to patent domain. The customizing method consists of following steps: 1) linguistically studying about characteristics of patent documents, 2) extracting unknown words from large patent documents and constructing large bilingual terminology, 3) extracting and constructing the patent-specific translation patterns 4) customizing the translation engine modules of the existing general MT system according to linguistic study about characteristics of patent documents, and 5) evaluating the accuracy of translation modules and the translation quality. This research was performed under the auspices of the MIC (Ministry of Information and Communication) of Korean government during 2005-2006. The translation accuracy of the customized English-Korean patent translation system is 82.43% on the average in 5 patent fields (machinery, electronics, chemistry, medicine and computer) according to the evaluation of 7 professional human translators. In 2006, the patent MT system started an on-line patent MT service in IPAC (International Patent Assistance Center) under MOCIE (Ministry of Commerce, Industry and Energy) in Korea. In 2007, KIPO (Korean Intellectual Property Office) tries to launch an English-Korean patent MT service.

• Language and Information
• /
• v.2 no.1
• /
• pp.79-105
• /
• 1998

This paper aims to describe a German-Korean machine translation system for nominal phrases. Besides, we have two subgoals. First, we are going to revea linguistic differences between two languages and propose a language-informational method fo overcome the differences. The method is based on an integrated model of translation knowledge, efficient information structure, and concordance selection. Then, we will show the statistical results about translation experiment and its evaluation as an evidence for the adequacy of our linguistic method and translation system itself.