• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.181-189
• /
• 2005

Due to grammatical similarities, even a one-to-one mapping between Korean and Japanese morphemes can usually result in a high quality Korean-to-Japanese machine translation. So most of Korean-to-Japanese machine translation are based on a one-to-one mapping relation. Most of Korean '-hada' verbs, which consist of a noun and '-hada', also correspond to Japanese '-suru' verbs, which consist of a noun and '-suru', so we generally use one-to-one mapping relation between them. However, the applications only by one-to-one mapping may sometimes result in incorrect Japanese correspondences in some cases that Korean 'hada' verbs don't correspond to Japanese 'suru' verbs. In these cases, we need to handle a noun and '-hada' as one translation unit. Therefore, this paper examined the characteristics of Korean '-hada' verb and proposed transfer rules of Korean 'hada' verb, applying for various states of input sentences such as discontinuity due to inserted words between a noun and '-hada', passivization, and modification of '-hada' verb. In an experimental evaluation, the proposed method was very effective for handling '-hada' verb in a Korean-to-Japanese machine translation, showing high quality of translation results.

• Language and Information
• /
• v.8 no.1
• /
• pp.101-116
• /
• 2004

This paper proposes a statistical model for the translation of prepositions in English-Korean machine translation. In the proposed model, statistical information acquired from unlabeled Korean corpora is used to choose the best translation from several possible translations. Such information includes functional word-verb co-occurrence information, functional word-verb distance information, and noun-postposition co-occurrence information. The model was evaluated with 443 sentences, each of which has a prepositional phrase, and we attained 71.3% accuracy.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.489-497
• /
• 2007

Named entity translation plays an important role in many applications, such as information retrieval and machine translation. In this paper, we focus on translating person names, the most common type of name entity in Korean-Chinese cross language information retrieval (KCIR). Unlike other languages, Chinese uses characters (ideographs), which makes person name translation difficult because one syllable may map to several Chinese characters. We propose an effective hybrid person name translation method to improve the performance of KCIR. First, we use Wikipedia as a translation tool based on the inter-language links between the Korean edition and the Chinese or English editions. Second, we adopt the Naver people search engine to find the query name's Chinese or English translation. Third, we extract Korean-English transliteration pairs from Google snippets, and then search for the English-Chinese transliteration in the database of Taiwan's Central News Agency or in Google. The performance of KCIR using our method is over five times better than that of a dictionary-based system. The mean average precision is 0.3490 and the average recall is 0.7534. The method can deal with Chinese, Japanese, Korean, as well as non-CJK person name translation from Korean to Chinese. Hence, it substantially improves the performance of KCIR.

• Journal of Korean Medical classics
• /
• v.24 no.4
• /
• pp.69-101
• /
• 2011

Based on the previous translation studies and "WHO-IST", we selected terminology, which are required the definition and explanation among jargon expressed in "Dongeuisusebowon Discourse on Nature and Act", and the procedure of the definition, explanation, and translation in Korean and English has been followed. The outcomes of this study are presented as below: First, based on the existing translation studies, Korean and English translation of "Dongeuisusebowon Discourse on Nature and Act" is provided. Second, few of Terminology in "Dongeuisusebowon(東醫壽世保元)" have been written in WHO-IST, even most of them have been standardized in terms of "Huang Di Nei Jing(黃帝內經)". Therefore, terminology related to Four-constitution medicine in WHO-IST would be required to be corrected, and unattatched terminology should be added in the future. Third, in order to standardize and globalize Four-constitution medicine, further definition, explanation, and translation studies of the rest of Dongeuisusebowon should be continued.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.403-408
• /
• 2022

This study analyzed the translation strategies of four Chinese translations of 『Who ate all the Sing a?』. As is well known, Park Wan-seo's works contain many psychological descriptions, abstract vocabulary, idioms, proverbs, dialects, etc., so when translating into Chinese, various translation strategies such as translation, interpretation, and creative translation are required. Although all four types studied in this paper are somewhat different depending on the translator, all translation strategies were used in a comprehensive way. As a result of the study, all four translation strategies used a strategy of direct translation of Chinese characters when translating geographical namesand names of people. The interpretational translation strategy was used for the translation of vocabulary that requires historical, social, cultural, and geography background interpretation. was utilized. The creative translation strategy was used when translating overlapping issues, political and historically sensitive issues, and issues related to Korean pronunciation and grammar. Based on the results of this study, it is expected that translation strategy research on various Chinese translations of Korean modern literature as well as various Chinese translations of Park Wan-seo will be expanded.

• 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.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.87-94
• /
• 2007

This paper introduces BEYTrans (Better Environment for Your TRANSlation), the first experimental environment for free online collaborative computer-aided translation. The requirements and functionalities related to individual translators and communities of translators are distinguished and described. These functionalities have been integrated in a Wiki-based complete environment, equipped with all currently possible asynchronous linguistic resources and translation aids. Functions provided by BEYTrans are also compared with existing CAT systems and ongoing experiments are discussed.

• Journal of Acupuncture Research
• /
• v.28 no.3
• /
• pp.121-129
• /
• 2011

Objectives : This study was to propose how to translate journal references into english for enhancing citation index of the journals published in the Korean Oriental Medical Society. Methods : Journal reference is mainly composed of author name, title or book name, journal name such as Index Medicus or publisher name, etc. In order to find the appropriate equivalents to the above major constituents, head words extracted from all the references of Journal of Korean Oriental Medical Society published in 2002 to 2009. A plan for English translation of the journal reference was formulated and the glossary was prepared. Plan for English translation of the journal reference : 1. Author: Author name was represented as capitalized last name and two initials of first name and listed up to six. If there are more, the first three or six authors were listed with 'et al'. 2. Terminology of traditional Korean medicine: Standard korean traditional medical terminology was one of the current representative dictionary with as much as 6040 headwords, which was needed to be translated into English in order to provide substantial equivalents available for English translation of journal reference. Therefor 4361 english equivalents were to be newly adopted except for 1679 overlapped with them in WHO-IST. Source oriented translation and target oriented translation were allowed to be appropriately selected depending on the condition. In addition, principle of English translation of acupoint,medicinal Herbs, Herbal formula and classical works were proposed. 3. Basically the names of journals should be set in italics and abbreviated according to the List of journals indexed for medline (formerly Index Medicus) published by the National Library of Medicine. however, abbreviation of korean oriental medical journals were not yet established. Thus establishment of tentative korean index medicus should be considered. Conclusions : For the enhancement of journal citation index of korean traditional medical journals, it was suggested that english translation of journal reference should be one of the alternatives enhancing citation rate.

• Cross-Cultural Studies
• /
• v.38
• /
• pp.145-190
• /
• 2015

The objective of this paper is to investigate translated individual words in J. S. Gale's "Choon Yang" in comparison with its original OkJoongHwa("獄中花") while referring to early modern bilingual dictionaries and missionaries' ethnography. Gale faced a lot of translation difficulties because the source text had a very different cultural system from the object text. OkJoongHwa was a Korean pansori novel which meant it included many Korean characteristics. However, Gale considered its Korean characteristics were deeply connected with Chinese classics. Even famous people and place names cited from the Chinese classics in OkJoongHwa represented the Korean thinking. Gale tried to faithfully translate the source text as much as possible whether the words were Chinese or Korean. In this paper, we deal with mostly various translation aspects of the Chinese-letter words in OkJoongHwa. Gale's first method to translate words made of Chinese Character is transliteration, the examples of which are the name of Chinese famous people and places, and Chinese poems. The second method is to parallel transliteration and English interpretation equivalent to the Chinese Character. The examples are the names of main characters like "Spring Fragrance or Choonyang," "Mongyong, or Dream-Dragon" and in his translation of word play in Osa (Commissioner), or Kamsa (Governor), kaiksa (a dead beggar). The third is literal translation of Chinese idiomatic phrases as Gale translated 侵魚落雁 into "She'd make the fishes to sink and the wild-geese to drop from the sky." The fourth is a little free translation of the title of public office, the various names of Korean yamen servants and the unique Korean clothing and ornaments. We expect Gale's many translation difficulties as we can see the translated long list of yamen clerks and Korean clothing and ornaments. After our investigation of his translation practices in "Choon Yang" we conclude that he tried to translate its literary language very faithfully though he could not avoid inevitable loss caused by the cultural difference involved in two languages. Gale's "Choon Yang" contributed to introducing the uniqueness of the classical Korean novel and Korean culture to the world more than any other English translation works of that time through his faithful translation.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.790-797
• /
• 2005

It is well-known that there are many similarities between Japanese and Korean language. For example, the order of words and the nature of the grammatical conjugation of both languages are almost the same. Another similarity is the frequent omission of the subject from a sentence. Moreover, both languages have honorific expressions and the identical concept for expressing nouns in terms of Chinese characters. Using these similarities, we have developed a word-to-word translation system which does away with any deep level analysis of syntactic and semantic structures of the two languages. If we use these similarities, the direct translation method is superior to the internal language translation method or transfer-based translation method. Although the MT system based on the direct translation method is more easily developed than the ones based on other methods, it may have a lot of difficulties when it tries to select the appropriate target word from ambiguous source verbs. In this paper, we propose a new algorithm to extract the meaning of substantives and to make use of the order of the extracted meaning. We could select $86.5\%$ appropriate verbs in the sample sentences from IPAL-verb-dictionary. $13.5\%$ indicates the cases in which we could not distinguish the meaning of substantives. We are convinced, however, that the succeeding rate can be increased by getting rid of the meaning of verbs thatare not used so often.