• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.21-29
• /
• 2022

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.

• Cross-Cultural Studies
• /
• v.45
• /
• pp.109-143
• /
• 2016

This article examines distinctive linguistic shifts of translational English in an effort to verify the validity of the translation universals hypotheses, including simplification, explicitation, normalization and leveling-out, which have been most heavily explored to date. A large-scale study involving comparable corpora of translated and non-translated English newspaper texts has been carried out to typify particular linguistic attributes inherent in translated texts. The main findings are as follows. First, by employing the parameters of STTR, top-to-bottom frequency words, and mean values of sentence lengths, the translational instances of simplification have been detected across the translated English newspaper corpora. In contrast, the portion of function words produced contrary results, which in turn suggests that this feature might not constitute an effective test of the hypothesis. Second, it was found that the use of connectives was more salient in original English newspaper texts than translated English texts, being incompatible with the explicitation hypothesis. Third, as an indicator of translational normalization, lexical bundles were found to be more pervasive in translated texts than in non-translated texts, which is expected from and therefore support the normalization hypothesis. Finally, the standard deviations of both STTR and mean sentence lengths turned out to be higher in translated texts, indicating that the translated English newspaper texts were less leveled out within the same corpus group, which is opposed to what the leveling-out hypothesis postulates. Overall, the results suggest that not all four hypotheses may qualify for the label translation universals, or at least that some translational predictors are not feasible enough to evaluate the effectiveness of the translation universals hypotheses.

• KLA journal
• /
• v.9 no.8
• /
• pp.8-20
• /
• 1968

이는 1965년 7월 중국도서관학회가 최종적으로 심의공포한 ‘도서관표준’의 번역임

• Annual Conference on Human and Language Technology
• /
• 1991.10a
• /
• pp.44-57
• /
• 1991

In the transfer machine translation, transfer dictionary decides the complexity of the transfer phase and the quality of translation according to the types and precision of informations supplied in the dictionary. Using the phrasal level translated informations within the human readable dictionary, human being translates a source sentence correctly and naturally. In this paper, we propose the verb transfer dictionary in which the various informations are constructed so the machine readable format that the Korean-to-English machine translation system can utilize them. In the proposed dictionary, we first provide the criterions by which an appropriate target verb is selected in phrase-to-phrase translations without an additional semantic analysis in transfer phase. Second, we provide the concrete sentence structure of a target verb so that we can resolve the expressive gaps between two languages and reduce the complexity of the various structure transfer in word-to-word translation.

• Nuclear industry
• /
• v.7 no.7 s.53
• /
• pp.32-38
• /
• 1987

본 논문은 지난 4월 11일 미국원자력학회(ANS) 한국지부의 월례기술토론회에서 ${\ulcorner}$The Future Outlook for Consistencies in Pacific Basin Codes and Standards${\lrcorner}$라는 제목으로 행한 특별강연문을 번역한 것이다.

• The Journal of the Korea Contents Association
• /
• v.17 no.10
• /
• pp.54-64
• /
• 2017

The purpose of this study was to analyze the cliche for English-Korean interpretation and translation with special reference to the cliche based on the Holy Bible texts. Cliches are figurative or literal expressions and are overused expressions in various different cultures. In addition, cliches are languages, a tool of communication in an appealing way. Therefore, cliches are must be clearly distinguished from the term of idioms that are figurative phrases with an implied meaning; the phrase is not to be taken literally. Also, cliches are the single most important factor that characterizes socioculturally. Through this empirical analysis on cliches we see that this study has conceptualized the meaning of cliche. Based on this result, I expect that anyone who researches English-Korean interpretation and translation field should be concerned about cliches. I hope this study will be a guide to the right uses of cliches in English language fields.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.603-608
• /
• 2023

본 연구는 한국어 Vision-Language Pre-training 모델 학습을 위한 대규모 시각-언어 멀티모달 데이터셋 구축에 대한 필요성을 연구한다. 현재, 한국어 시각-언어 멀티모달 데이터셋은 부족하며, 양질의 데이터 획득이 어려운 상황이다. 따라서, 본 연구에서는 기계 번역을 활용하여 외국어(영문) 시각-언어 데이터를 한국어로 번역하고 이를 기반으로 생성형 AI를 활용한 데이터셋 구축 방법론을 제안한다. 우리는 다양한 캡션 생성 방법 중, ChatGPT를 활용하여 자연스럽고 고품질의 한국어 캡션을 자동으로 생성하기 위한 새로운 방법을 제안한다. 이를 통해 기존의 기계 번역 방법보다 더 나은 캡션 품질을 보장할 수 있으며, 여러가지 번역 결과를 앙상블하여 멀티모달 데이터셋을 효과적으로 구축하는데 활용한다. 뿐만 아니라, 본 연구에서는 의미론적 유사도 기반 평가 방식인 캡션 투영 일치도(Caption Projection Consistency) 소개하고, 다양한 번역 시스템 간의 영-한 캡션 투영 성능을 비교하며 이를 평가하는 기준을 제시한다. 최종적으로, 본 연구는 ChatGPT를 이용한 한국어 멀티모달 이미지-텍스트 멀티모달 데이터셋 구축을 위한 새로운 방법론을 제시하며, 대표적인 기계 번역기들보다 우수한 영한 캡션 투영 성능을 증명한다. 이를 통해, 우리의 연구는 부족한 High-Quality 한국어 데이터 셋을 자동으로 대량 구축할 수 있는 방향을 보여주며, 이 방법을 통해 딥러닝 기반 한국어 Vision-Language Pre-training 모델의 성능 향상에 기여할 것으로 기대한다.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.247-251
• /
• 2001

명사 의미 부류 체계는 언어 처리의 다양한 분야에서 그 필요성이 부각되고 있다. 예를 들어, 기계 번역에 있어서의 단어 의미의 중의성 해소(word sense disambiguation), 정보검색 시스템에서도 재현율과 정확률의 향상, 추론 시스템 등을 위하여 명사 의미 부류는 중요한 역할을 한다. 명사 의미 부류 체계의 이러한 중요성 때문에 여러 온톨로지(ontology)가 기존에 구축되어 있다. 그런데 이러한 온톨로지들은 대개 순수한 개념적 기준에 입각한 것이며 단어의 통사적 특성을 별로 고려하고 있지 않다. 정보검색 시스템이나 추론 시스템의 경우에는 통사적 고려가 별로 중요하지 않을 수 있으나 기계번역의 경우 통사적 특성에 대한 고려가 매우 중요하다. 이러한 점에 주목하여 21세기 세종계획 전자사전 분과에서는 개념적 기준과 통사적 기준을 모두 고려하여 명사 의미 부류 체계를 구축하고 있다. 즉, 해당 부류에 속하는 명사들이 결합할 수 있는 술어(적정 술어) 등의 통사적 요인을 중요시하여 명사들을 분류하고 있는 것이다. 이에 따라 세종 체언 사전의 모든 명사들에 대해 의미부류 정보가 주어지고, 용언 사전의 용언의 각 논항에 대한 선택제약 정보도 이 명사 의미부류 체계를 이용하여 제시되고 있다. 이러한 정보들은 한국어 처리에 중요한 자료로 이용될 것이다.

• Korean journal of communication and information
• /
• v.78
• /
• pp.206-242
• /
• 2016

This study dealt with the U.S. government's book translation project as a part of its public diplomacy to gain the Korean people's 'minds and thoughts' in the midst of cultural Cold War from the end of World War II to the late 1950s. It was found that the U.S. book translation project was begun during the U.S. military occupation of South Korea, though with minimum efforts, and reached its peak in the late 1950s, In general, the purposes of the U.S. book translation project in South Korea was as follows: to emphasize the supremacy of American political and economic systems; to criticize the irrationality of communism and conflicts in the communist societies; to increase the Korean people's understanding of the U.S. foreign policies; to publicize the achievement of the U.S. people in the areas of arts, literature, and sciences. In the selection of books for translation, any ones were excluded which might contradict to U.S. foreign policy or impair U.S. images abroad. It must be noted that publications of a few Korean writers' books were supported by the project, if they were thought to be in service for its purposes. Even some Japanese books, which were produced by the U.S. book translation project in Japan, were utilized for the best effects of the project in South Korea. It may be conceded that the U.S. book translation project contributed a little bit to the compensation for the dearth of knowledge and information in South Korea at that time. However, the project may have distorted the Korean people's perspectives toward the U.S. and world, owing to the book selection in accordance with the U.S. government's policy guidance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.461-467
• /
• 2017

As the number of smart devices increases, e-book contents and services are proliferating. However, the text based e-book is difficult for a hearing-impairment person to understand. In this paper, we developed an android based application in which we can choose an e-book text file and each sentence is translated to sign-language elements which are shown in videos that are retrieved from the sign-language contents server. We used the korean sentence to sign-language translation algorithm based on the morpheme analysis. The proposed translation algorithm consists of 3 stages. Firstly, some elements in a sentence are removed for typical sign-language usages. Secondly, the tense of the sentence and the expression alteration are applied. Finally, the honorific forms are considered and word positions in the sentence are revised. We also proposed a new method to evaluate the performance of the translation algorithm and demonstrated the superiority of the algorithm through the translation results of 100 reference sentences.