• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.27-32
• /
• 2013

본 논문은 잘 알려지지 않은 언어 쌍에 대해서 병렬말뭉치(parallel corpus)로부터 자동으로 이중언어 사전을 추출하는 방법을 제안하였다. 이 방법은 중간언어(pivot language)를 매개로 하고 문맥 벡터를 생성하기 위해 공개된 단어 정렬 도구인 Anymalign을 사용하였다. 그 결과로 초기사전(seed dictionary)을 사용한 문맥벡터의 번역 과정이 필요 없으며 통계적 방법의 약점인 낮은 빈도수를 가지는 어휘에 대한 번역 정확도를 높였다. 또한 문맥벡터의 요소 값으로 특정 임계값 이상을 가지는 양방향 번역 확률 정보를 사용하여 상위 5위 이내의 번역 정확도를 크게 높였다. 본 논문은 두 개의 서로 다른 언어 쌍 한국어-스페인어 그리고 한국어-프랑스어 양방향에 대해서 각각 이중언어 사전을 추출하는 실험을 하였다. 높은 빈도수를 가지는 어휘에 대한 번역 정확도는 이전 연구에서 보인 실험 결과에 비해 최소 3.41% 최대 67.91%의 성능 향상을 보였고 낮은 빈도수를 가지는 어휘에 대한 번역 정확도는 최소 5.06%, 최대 990%의 성능 향상을 보였다.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.27-35
• /
• 2021

Automatic post editing is a research field that aims to automatically correct errors in machine translation results. This research is mainly being focus on high resource language pairs, such as English-German. Recent APE studies are mainly adopting transfer learning based research, where pre-training language models, or translation models generated through self-supervised learning methodologies are utilized. While translation based APE model shows superior performance in recent researches, as such researches are conducted on the high resource languages, the same perspective cannot be directly applied to the low resource languages. In this work, we apply two transfer learning strategies to Korean-English APE studies and show that transfer learning with translation model can significantly improves APE performance.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.33 no.10
• /
• pp.48-52
• /
• 2015

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1183-1192
• /
• 1988

In this paper, we describe heuristic information-added morphological dictionary and connection table, and automatic MUNJEUL separation process on the basis of least cost method for efficient morphological analysis. It is simplified the composition of connection and inflective word information by mutually interconnect conjugation table with connection tables. As a result, the applicability of system is increased. Translation dictionary consists of analysis and generation part and, increase the applicability by describing frequently using termination phrase which is extracted statistically as idiom and the procedure directly on the dictionary for the efficiency of analysis process and more natural generation of translation sentence.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.163-170
• /
• 2017

Despite the rise of studies in spoken to sign language translation, low-resource problems of sign language corpus have been rarely addressed. As a first step towards translating from spoken to sign language, we addressed the problems arising from resource scarcity when translating spoken language to manual signals translation using statistical machine translation techniques. More specifically, we proposed three preprocessing methods: 1) paraphrase generation, which increases the size of the corpora, 2) lemmatization, which increases the frequency of each word in the corpora and the translatability of new input words in spoken language, and 3) elimination of function words that are not glossed into manual signals, which match the corresponding constituents of the bilingual sentence pairs. In our experiments, we used different types of English-American sign language parallel corpora. The experimental results showed that the system with each method and the combination of the methods improved the quality of manual signals translation, regardless of the type of the corpora.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.23-28
• /
• 2012

번역을 지원하는 도구로 자동 번역 시스템을 효율적으로 활용하기 위해 중요한 것은 자동 번역에 적합하도록 원문을 작성하거나 이미 작성된 원문에 대한 전처리 작업을 하는 것이다. 본 연구의 궁극적인 목표는 제품 설명서 작성자가 통제언어 체커를 통해 통제언어 규칙들을 적용하여 원문을 작성하도록 하는 것이다. 본 논문은 그 중간 단계로써 제품 설명서에 나타나는 문제 사항이 번역 품질에 어떠한 영향을 미치는지 밝혀내는 것을 목적으로 한다. 연구 대상은 제품 설명서에서 자동 번역의 성능을 저해시키는 요소 중 중의적 명사 수식 구문이다. 이러한 명사 수식 구문들은 분석 단계에서 구조적인 모호성을 초래하여 한국어 분석의 정확도를 떨어뜨리기 때문에 결과적으로 번역 품질을 악화시킬 수 있다. 이를 검증하기 위해 우선 제품 설명서 데이터를 분석하여 자동 번역 결과에 부정적인 영향을 미치는 명사 수식 구문을 다음과 같이 4가지로 유형화 하였다. (유형 1) 관형격 명사구 + 명사 병렬 접속, (유형 2) 동사의 관형형이 수식하는 명사구 + 명사 병렬 접속, (유형 3) 관형격 조사 '의' 중복, (유형 4) 병렬 접속어를 잘못 쓴 경우, 각각의 유형에 대해서 한국어 분석 단계에서 발생할 수 있는 문제에 대해 설명하였으며, 문제 사항에 대해 통제언어 규칙을 제시하였다. 통제언어 규칙에 따라 중의적 명사 수식 구문을 수정한 결과, 한국어 원문의 번역결과보다 한국어 수정문의 번역결과가 작성자의 의도를 더 잘 나타낸다는 것을 확인할 수 있었다.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.199-208
• /
• 2021

Automatic Post Editing(APE) is the study that automatically correcting errors included in the machine translated sentences. The goal of APE task is to generate error correcting models that improve translation quality, regardless of the translation system. For training these models, source sentence, machine translation, and post edit, which is manually edited by human translator, are utilized. Especially in the recent APE research, multilingual pretrained language models are being adopted, prior to the training by APE data. This study deals with multilingual pretrained language models adopted to the latest APE researches, and the specific application method for each APE study. Furthermore, based on the current research trend, we propose future research directions utilizing translation model or mBART model.

• Cross-Cultural Studies
• /
• v.51
• /
• pp.329-356
• /
• 2018

Types of emotional expressions are comprised of vocabulary that describes emotion and composition of sentences to express emotion such as an exclamatory sentence and a rhetorical question, expressions of interjection, adverbs of attitude for an idea, and a style of writing. This study is focused on vocabulary that describes emotion and analyzes the aspect of translation when emotional expression of 'Kyo(驚)' is shown in "Kokoro". As a result, the aspect of translation for expression of 'Kyo(驚)' showed that it was translated to vocabulary as suggested in the dictionary in some cases. However, it was not always translated as suggested in the dictionary. Vocabulary that describes the emotion of 'Kyo(驚)' in Japanese sentences is mostly translated to corresponding parts of speech in Korean. Some adverbs needed to add 'verbs' when they were translated. Different vocabulary was added or used to maximize emotion. However, the corresponding part of speech in English was different from Korean. Examples of Japanese sentences expressing 'Kyo(驚)' by verbs were translated to expression of participles for passive verbs such as 'surprise' 'astonish' 'amaze' 'shock' 'frighten' 'stun' in many cases. Idioms were also translated with focus on the function of sentences rather than the form of sentences. Those expressed in adverbs did not accompany verbs of 'Kyo(驚)'. They were translated to expression of participles for passive verbs and adjectives such as 'surprise' 'astonish' 'amaze' 'shock' 'frighten' 'stun' in many cases. Main agents of emotion were showat the first person and the third person in simple sentences. Translation of emotional expressions when a main agent was the first person showed that the fundamental word order of Japanese was translated as in Korean. However, adverbs of time and adverbs of degree were ended to be added. The first person as the main agent of emotion was positioned at the place of subject when it was translated in English. However, things or causes of events were positioned at the place of subject in some cases to show the degree of 'Kyo(驚)' which the main agent experienced. The expression of conjecture and supposition or a certain visual and auditory basis was added to translate the expression of emotion when the main agent of emotion was the third person. Simple sentences without the main agent of emotion showed that their subjects could be omitted even if they were essential components because they could be known through context in Korean. These omitted subjects were found and translated in English. Those subjects were not necessarily human who was the main agent of emotion. They could be things or causes of events that specified the expression of emotion.

• 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.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.3
• /
• pp.64-70
• /
• 2004

Korean and Japanese have same structure of sentences because they belong to same family of languages. So, The transfer driven machine translation is most efficient to translate each other. This paper introduce a method which creates a transfer dictionary for Token Based Transfer Driven Koran-Japanese Machine Translation(TB-TDMT). If the transfer dictionaries are created well, we get rid of useless effort for traditional parsing by performing shallow parsing. The semi-parser makes the dependency tree which has minimum information needed output generating module. We constructed the transfer dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 900 utterances which are collected from travel planning domain. The success-ratio of our system is $92\%$ on restricted testing environment and $81\%$ on unrestricted testing environment.