• Title/Summary/Keyword: 이중 언어

Search Result 246, Processing Time 0.027 seconds

Bilingual Word Embedding using Subtitle Parallel Corpus (자막 병렬 코퍼스를 이용한 이중 언어 워드 임베딩)

  • Lee, Seolhwa;Lee, Chanhee;Lim, Heuiseok
    • Proceedings of The KACE
    • /
    • 2017.08a
    • /
    • pp.157-160
    • /
    • 2017
  • 최근 자연 언어 처리 분야에서는 단어를 실수벡터로 임베딩하는 워드 임베딩(Word embedding) 기술이 많은 각광을 받고 있다. 최근에는 서로 다른 두 언어를 이용한 이중 언어 위드 임베딩(Bilingual word embedding) 방법을 사용하는 연구가 많이 이루어지고 있는데, 이중 언어 워드 임베딩에서 임베딩 절과의 질은 학습하는 코퍼스의 정렬방식에 따라 많은 영향을 받는다. 본 논문은 자막 병렬 코퍼스를 이용하여 밑바탕 어휘집(Seed lexicon)을 구축하여 번역 연결 강도를 향상시키고, 이중 언어 워드 임베딩의 사천(Vocabulary) 확장을 위한 언어별 연결 함수(Language-specific mapping function)을 학습하는 새로운 방식의 모델을 제안한다. 제안한 모델은 기존 모델과의 성능비교에서 비교할만한 수준의 결과를 얻었다.

  • PDF

Enhancing Performance of Bilingual Lexicon Extraction through Refinement of Pivot-Context Vectors (중간언어 문맥벡터의 정제를 통한 이중언어 사전 구축의 성능개선)

  • Kwon, Hong-Seok;Seo, Hyung-Won;Kim, Jae-Hoon
    • Journal of KIISE:Software and Applications
    • /
    • v.41 no.7
    • /
    • pp.492-500
    • /
    • 2014
  • This paper presents the performance enhancement of automatic bilingual lexicon extraction by using refinement of pivot-context vectors under the standard pivot-based approach, which is very effective method for less-resource language pairs. In this paper, we gradually improve the performance through two different refinements of pivot-context vectors: One is to filter out unhelpful elements of the pivot-context vectors and to revise the values of the vectors through bidirectional translation probabilities estimated by Anymalign and another one is to remove non-noun elements from the original vectors. In this paper, experiments have been conducted on two different language pairs that are bi-directional Korean-Spanish and Korean-French, respectively. The experimental results have demonstrated that our method for high-frequency words shows at least 48.5% at the top 1 and up to 88.5% at the top 20 and for the low-frequency words at least 43.3% at the top 1 and up to 48.9% at the top 20.

Changes in fundamental frequency depending on language, context, and language proficiency for bilinguals (한국어-영어 이중언어 화자의 사용 언어, 문맥, 언어 능숙도에 따른 기본 주파수 변화)

  • Yoon, Somang;Mok, Sora;Youn, Jungseon;Han, Jiyun;Yim, Dongsun
    • Phonetics and Speech Sciences
    • /
    • v.11 no.1
    • /
    • pp.9-18
    • /
    • 2019
  • The purpose of this study is to determine whether the mean fundamental frequency (F0) changes depending on language, task, or language proficiency for Korean-English bilinguals. A total of forty-eight Korean-English speakers (28 balanced bilinguals and 20 Korean dominant bilinguals) participated in the study. Participants were asked to read aloud two types of tasks in English and Korean. For statistical analyses, the language ${\times}$ task two-way repeated ANOVAs were conducted within the balanced bilingual group first, and then group ${\times}$ language two-way mixed ANOVAs. The results showed that the females in both bilingual groups changed their mean F0 depending on the language they used and the tasks (p<.05), whereas no significant results were found in the males in either group under any conditions. The mean fundamental frequency in the Korean reading task was significantly higher than that in the English reading task for females in both balanced and Korean dominant bilingual groups. Thus, changes in mean F0 depending on language and context may reflect gender-specific characteristics, and females seem to be more sensitive to the socio-cultural standards that are imposed on them.

Research trends of bilingual education for children from multicultural families : focused on foreigner parent's language education (국내 다문화가정 자녀를 위한 이중언어교육 연구동향 -이주부모나라 언어교육을 중심으로-)

  • Chen, Jia;Huang, Hai-Ying
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.6 no.10
    • /
    • pp.107-120
    • /
    • 2016
  • The purpose of this study is to analyze research trends of bilingual education which are focused on foreigner parent's language education for children from multicultural families in South Korea. After searching, total 36 research papers were selected and analyzed. Results from this study showed that, (1) relevant researches started from 2009, later then the number of researches kept about 4-6 yearly and reached the peak of 11 (31%) in 2004; (2) a large majority (75%) of the analyzed researches published in the magazines relative to a field of language education or children education; (3) diverse research methods were employed, and the number of researches applied on qualitative research methods is similar with on quantitative ; (4) the researches mainly studied on the members of multicultural families (67%), and 10 analyzed researches investigated parents and children together 28%, and 9 targeted on parents or one of them (25%), and 5 just on the children from multicultural families (14%). and, (5) The research topics mainly divided into four fields current bilingual education programs (31%), bilingual education (31%), interaction related to bilingual education (22%), suggestion on policy improvement(17%). Based on the results, discussions and implications for further research and practice on bilingual education and foreigner parent's language education will be provided.

Utilizing Local Bilingual Embeddings on Korean-English Law Data (한국어-영어 법률 말뭉치의 로컬 이중 언어 임베딩)

  • Choi, Soon-Young;Matteson, Andrew Stuart;Lim, Heui-Seok
    • Journal of the Korea Convergence Society
    • /
    • v.9 no.10
    • /
    • pp.45-53
    • /
    • 2018
  • Recently, studies about bilingual word embedding have been gaining much attention. However, bilingual word embedding with Korean is not actively pursued due to the difficulty in obtaining a sizable, high quality corpus. Local embeddings that can be applied to specific domains are relatively rare. Additionally, multi-word vocabulary is problematic due to the lack of one-to-one word-level correspondence in translation pairs. In this paper, we crawl 868,163 paragraphs from a Korean-English law corpus and propose three mapping strategies for word embedding. These strategies address the aforementioned issues including multi-word translation and improve translation pair quality on paragraph-aligned data. We demonstrate a twofold increase in translation pair quality compared to the global bilingual word embedding baseline.

Bilingual Teaching-Learning Plan for Migrant Youths Based on the Waldorf Program (발도르프 프로그램을 준용한 중도입국 청소년의 이중언어 교수-학습 방안)

  • Moon, Kyung-im
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2019.01a
    • /
    • pp.161-164
    • /
    • 2019
  • 한국 사회는 빠르게 다문화 사회로 진입되고 있어 인구 구성과 집단이 다양해 질것으로 전망하고 있다. 다양한 형태의 가족 중 중도입국 청소년들의 비율이 점점 증가하고 있다. 대부분의 중도입국 청소년들은 준비가 전혀 이루어진 않은 상태에서 우리나라에 입국하는 실정이므로 언어장벽에서 진로장벽에 이르기 까지 매우 취약한 여건과 불안정한 환경에 처해 있는 것이다. 이를 해결하는 방안으로 국가나 지방자치단체는 물론 각급 교육기관에서 다양한 프로그램으로 서비스가 지원되고 있으나 사업 간의 중복성과 일부 비효율적인 전달체계와 운영, 예산과 인력 낭비로 인하여 효과성을 낮추는 경향이 있다. 본 논문에서는 중도입국 청소년들의 발달주기, 학령주기, 한국어 구사 능력에 따라 개인의 능력에 따른 맞춤형 언어교육으로 올바르게 성장하도록 도움을 주는 방안을 제시한다. 제시한 내용은 이중언어 교육방법과 발도르프 교육 프로그램을 준용한 교수-학습 방안이다.

  • PDF

A Study on the Experiences of Multi-cultural Family Mothers in Children's Bilingual Education (다문화가정 어머니가 경험한 자녀의 이중언어교육에 관한 연구)

  • Cho, Seung-Suk;Kim, Hee-Soon
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.14 no.11
    • /
    • pp.5549-5558
    • /
    • 2013
  • This study is aimed at qualitatively looking into multi-cultual family mothers' experiences in children's bilingual education. The subjects for the study were seven married immigrant Vietnamese women with elementary school children who have recently finished bilingual education. After recording their interviews and then transcribing them, the data was analyzed by utilizing comparative analysis method. The results were divided into three categories of experiences: emotional, identical, and relational aspects. The results of this study will offer information about necessary support for bilingual education to multi-cultural family members.

The Processing System of English for Korean : Focused on the Interaction with Native Language Processing (한국인의 영어처리의 기제 : 모국어처리와의 상호작용을 중심으로)

  • Lee, Chang-H.;Kang, Bong-Kyeng
    • Annual Conference on Human and Language Technology
    • /
    • 2004.10d
    • /
    • pp.240-247
    • /
    • 2004
  • The purpose of this study was to investigate the role of phonology in lexical access of bilingual processing for Korean-English bilinguals. Four experiments have been conducted in order to adjudicate the nonselective lexical access hypothesis, which argues simultaneous phonological activation of two bilingual languages, and the selective lexical access hypothesis, which argues phonological activation of only one bilingual language. The results showed that the Korean target word processing was significantly affected by the phonological manipulation of the English prime word(Exp. 2). Similarly, the English target word processing showed the tendencies that it is affected by the phonological manipulation of the Korean prime word(Exp. 2). This results indicates that the phonological information of another bilingual language is automatically activated when we process one of bilingual languages, and the process of English, which is the second language for most Korean, is phonologically activated.

  • PDF

An Analysis of Korean Domestic Research Trend in English Education and Bi- lingualism of Young Children (유아교육 및 아동학 관련 국내 학회지에 발표된 영어교육/이중언어발달 관련 논문분석)

  • Ahn, Eun Suk;Kim, Yeon Ha
    • Korean Journal of Childcare and Education
    • /
    • v.5 no.1
    • /
    • pp.81-101
    • /
    • 2009
  • This study analyzed a total of 37 studies about bi-lingulism and English education as a foreign language published in 8 academic journals in early childhood education or child development fields. Research topics, participants, methods, and variables in the studies were categorized and descriptively analyzed. The research findings which had been statistically investigated were also summarized. The most frequently studied research topics were children's development and English education program exposure, actual conditions of English education in preschool settings and effectiveness of specific English programs for preschool children. However, children's home characteristics were seldom included as research variables and no research investigated so called English preschools. Several studies reported that bi-lingual children may have different language development paths from mono-lingual children but they eventually have comparable language abilities to mono-lingual children. Also some studies reported that, when learning English as a foreign language in school settings, older children can handle more information regarding English than younger children, resulting in better outcomes of older children. Exposure to two languages in early childhood seems to contribute to young children's meta linguistic awareness but the long term effect of English education in early childhood should be further studied. Several English education programs for preschool settings were developed and the effectiveness were investigated. Even though most of them reported that their programs were effective to children's English ability or interests, the results should be carefully interpreted because their research designs and methods were not rigorous.

  • PDF

Performance Improvement of Bilingual Lexicon Extraction via Pivot Language and Word Alignment Tool (중간언어와 단어정렬을 통한 이중언어 사전의 자동 추출에 대한 성능 개선)

  • Kwon, Hong-Seok;Seo, Hyeung-Won;Kim, Jae-Hoon
    • 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.

  • PDF