다국어 자동 통번역을 위한 공통 변환 기반 하이브리드 자동 번역 방법

최승권,김영길 한국외국어대학교 통번역연구소 2016 통번역학연구 Vol.20 No.3

Along with the advancement of speech recognition technology and machine translation technology in addition to the fast distribution of mobile devices, automatic speech translation technology no longer remains as a subject of research as it has become popularized throughout many users. The goal of this paper is to describe the method of hybrid machine translation based on common transfer for multilingual speech and machine translation. As of 2012, there are different bilingual machine translation systems such as Korean-to-English, English-to-Korean, Korean-to-Japanese, Japanese-to-Korean, Korean-to-Chinese, and Chinese-to-Korean machine translation systems in Korea. An increase in the number of tourists is expected due to the fact that the Winter Olympic Games will be held in Korea in 2018. Budget problem prevents us from employing a sufficient number of human interpreters who can fluently interpret such languages as Spanish, French, German, and Russian. For this reason, consumers such as the Korea Tourism Organization and speech translation service providers demand a multilingual speech and machine translation system. We are developing a multilingual speech and machine translation system aiming for multilingual expansibility and high-quality translation accuracy.

인공신경망 번역 엔진을 활용한 멀티링구얼 문법 교육

박강훈(Park, Kang-Hun) 한국일본문화학회 2019 日本文化學報 Vol.0 No.80

This paper aims to provide a Korean, Japanese, and English multilingual grammar education model using Google Translate. This research is conducted as part of a long-term research project called ‘Construction of Korean, Japanese, and English multilingual education models for Korean adult learners, especially university students majoring in Japanese language and literature’. Park (to appear) claims that the algorithm of the neural machine translation system and the multilingual education model are similar based on the following two points: (i) the theoretical background, (ii) transfer learning. Based on these facts, Park (to appear) states that we need to develop teaching methods of multilingual education using neural machine translation engines such as Google Translate in the future. Therefore, this paper proposes that Google Translate is applicable to Korean, Japanese, and English multilingual grammar education. Further, marking the first attempt of the same, this paper deals with the grammatical category of ‘tense and aspect’. The study on the multilingual grammar teaching method using Google Translate is being considered for active usage in the future, because this research and Google Translate set the common goal of ‘multilingual use’.

ChatGPT를 활용한 멀티링구얼 교육의 가능성에 대해서 - 일본어・영어 멀티링구얼 교육을 중심으로 -

신의식 한국외국어대학교 일본연구소 2023 日本硏究 Vol.- No.98

In this paper, we observed and examined various cases of the potential use of ChatGPT in multilingual education. To facilitate this discussion, we first confirmed how ChatGPT is currently being used in other educational domains and considered its applications. We also examined the teaching methods in the field of multilingual education and how they are implemented in Japanese language specialization (Japanese linguistics and education). Upon reviewing previous research, although limited in number, cases of multilingual education in Japanese and English using neural machine translation engines in their classes were identified. On the other hand, in this paper, we proposed the potential use of ChatGPT in multilingual education, evolving beyond traditional neural machine translation engines based on ChatGPT’s linguistic capabilities. Looking at the examples here, ChatGPT can generate various materials suitable for use in multilingual education in the domains of grammar, conversation, and text translation. However, effectively utilizing these materials requires the addition of content based on the knowledge of educators and the correction of any erroneous information. In conclusion, ChatGPT is believed to be a valuable tool in multilingual education with its exceptional linguistic capabilities.

New Perspectives on Multilingualism in a Context of the Fourth Industrial Revolution

Yang-Soon Kim(Yang-Soon Kim) 한국캐나다학회 2020 Asia-Pacific Journal of Canadian Studies (APJCS) Vol.26 No.1

This paper is to examine four core factors of multilingualism in a context of diversity and convergence of the Fourth Industrial Revolution Era. Since multilingualism is the natural potential available to everyone without unusual exceptions, multilingualism should be an ideal model as the norm almost in every field including policies and educational practices. Together with Canadian bilingualism, glocalized multilingualism has recently been a trend that we cannot resist from the new perspective of diversity in response to the current environment. Especially in the Era of the Fourth Industrial Revolution, multilingualism should be a key concept for a natural development of the global society. Multilingualism including bilingualism is the best route which we have to follow cognitively, socially and linguistically. In this paper, new perspectives on the legitimacy of multilingualism are discussed with positive effects in terms of four factors in the context of the Fourth Industrial Revolution: sustainability in glocalization, equity, World Englishes and machine translation.

다언어주의와 언어교육정책

김양순 국제문화기술진흥원 2020 The Journal of the Convergence on Culture Technolo Vol.6 No.1

우리는 이 연구에서 다언어주의 맥락에서의 지속가능한 언어교육정책을 고찰하고자 한다. 인구의 다수가 다언 어적이므로 다언어구사자들이 기준이 되는 다언어정책이 교육에서 우리가 채택할 수 있는 최선의 방법이다. 전통적으 로 다언어사회였던 미국의 언어교육정책을 분석하여 한국사회의 언어교육정책에 관한 시사점을 모색하고자 한다. 다 언어교육정책의 채택 동기와 정당성을 지속가능성, 정체성, 공정성, 세계영어, 기계번역, 그리고 보편문법이라는 6 가 지 다른 관점에서 분석한다. 언어정책의 모델로 미국에서는 영어플러스(영어+n) 정책을 제안하며, 유사하게 한국에서 는 한국어플러스(한국어+n) 정책을 언어교육현장에서의 최선의 언어정책모델로 제안한다. 이러한 플러스(+n)정책은 모국어와 해당국가의 다언어주의를 형성하는 다른 외래어 둘 다의 유창성을 목표로 하며 이때 다언어정책은 이중언 어정책도 포함한다. 특히 4차 산업혁명시대의 맥락인 다양성과 융합의 시대에 언어다양성과 다언어정책은 해결해야할 문제가 아니라 보호되고 유지되어야할 권리이며 자산으로 간주되어야하고 언어교육정책 또한 다언어주의의 관점에서 다루어져야 한다. This paper is to analyze the language education policy in the context of multilingualism. As the majority of the population are multilingual, language policy should be centered on the multilingual speakers as the norm, and multilingual language policy is the best route which we can follow as a language policy in education. The motivation and legitimacy of the multilingual policies are suggested in terms of 6 different perspectives: identity, sustainability, equity, World Englishes, machine translation, and Universal Grammar (UG). As a model of language policy, the English-Plus (i.e., English+n) policy and similarly the Korean-Plus (i.e., Korean+n) policy are suggested to be the most appropriate language policies in the field of education in America and Korea respectively. These plus policies aim at bilingual fluency in both the native language and other foreign languages that are constitutive of the multilingualism of the country in which the bilingualism is treated as a variant of multilingualism. In a period of convergence and diversity in the 4th Industrial Revolution, language diversity and multilingual policy should be considered as a right to be protected or as a resource to be conserved rather than as a problem to be solved.

공통변환 기반 다국어 자동번역을 위한 언어학적 모델링

최승권 ( Sung Kwon Choi ),김영길 ( Young Gil Kim ) 한국언어정보학회 2014 언어와 정보 Vol.18 No.1

Multilingual machine translation means the machine translation that is for more than two languages. Common transfer means the transfer in which we can reuse the transfer rules among similar languages according to linguistic typology. Therefore, the multilingual machine translation based on common transfer is the multilingual machine translation that can share the transfer rules among languages with similar linguistic typology. This paper describes the linguistic modeling for multilingual machine translation based on common transfer under development. This linguistic modeling consists of the linguistic devices such as 1) multilingual common Part-of-Speech set, 2) multilingual common transfer format, 3) multilingual common transfer chunking, and 4) multilingual common transfer rules based on linguistic typology. Validity of this linguistic modeling for multilingual machine translation is shown in the simulation. The multilingual machine translation system based on common transfer including Korean, English, Chinese, Spanish, and French will be developed till 2018.

언어적 특성과 서비스를 고려한 딥러닝 기반 한국어 방언 기계번역 연구

임상범,박찬준,양영욱 한국융합학회 2022 한국융합학회논문지 Vol.13 No.2

Based on the importance of dialect research, preservation, and communication, this paper conducted a study on machine translation of Korean dialects for dialect users who may be marginalized. For the dialect data used, AIHUB dialect data distributed based on the highest administrative district was used. We propose a many-to-one dialect machine translation that promotes the efficiency of model distribution and modeling research to improve the performance of the dialect machine translation by applying Copy mechanism. This paper evaluates the performance of the one-to-one model and the many-to-one model as a BLEU score, and analyzes the performance of the many-to-one model in the Korean dialect from a linguistic perspective. The performance improvement of the one-to-one machine translation by applying the methodology proposed in this paper and the significant high performance of the many-to-one machine translation were derived. 본 논문은 방언 연구, 보존, 의사소통의 중요성을 바탕으로 소외될 수 있는 방언 사용자들을 위한 한국어 방언 기계번역 연구를 진행하였다. 사용한 방언 데이터는 최상위 행정구역을 기반으로 배포된 AIHUB 방언 데이터를 사용하였다. 방언 데이터를 바탕으로 Transformer 기반의 copy mechanism을 적용하여 방언 기계번역기의 성능 향상을 도모하는 모델링 연구와 모델 배포의 효율성을 도모하는 Many-to-one 기반의 방언 기계 번역기를 제안한다. 본 논문은 one-to-one 모델과 many-to-one 모델의 성능을 비교 분석하고 이를 다양한 언어학적 시각으로 분석하였다. 실험 결과 BLEU점수를 기준으로 본 논문이 제안하는 방법론을 적용한 one-to-one 기계번역기의 성능 향상과 many-to-one 기계번역기의 유의미한 성능을 도출하였다.