• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• pp.1535-1545
• /
• 2022

Sign language has completely different meaning depending on the direction of the hand or the change of facial expression even with the same gesture. In this respect, it is crucial to capture the spatial-temporal structure information of each movement. However, sign language translation studies based on Sign2Gloss2Text only convey comprehensive spatial-temporal information about the entire sign language movement. Consequently, detailed information (facial expression, gestures, and etc.) of each movement that is important for sign language translation is not emphasized. Accordingly, in this paper, we propose Spatial-temporal Keypoints Centered Sign2Gloss2Text Translation, named STKC-Sign2 Gloss2Text, to supplement the sequential and semantic information of keypoints which are the core of recognizing and translating sign language. STKC-Sign2Gloss2Text consists of two steps, Spatial Keypoints Embedding, which extracts 121 major keypoints from each image, and Temporal Keypoints Embedding, which emphasizes sequential information using Bi-GRU for extracted keypoints of sign language. The proposed model outperformed all Bilingual Evaluation Understudy(BLEU) scores in Development(DEV) and Testing(TEST) than Sign2Gloss2Text as the baseline, and in particular, it proved the effectiveness of the proposed methodology by achieving 23.19, an improvement of 1.87 based on TEST BLEU-4.

• 대한불안의학회지
• /
• 제19권1호
• /
• pp.1-9
• /
• 2023

Objective : To translate and adapt the Social Appearance Anxiety Scale into Korean and validate the Korean version of the social appearance anxiety scale, which measures the fear and anxiety about being negatively evaluated by others based on one's overall appearance, including body shape. Methods : For item translation and adaptation, six bilingual translators participated in the process of forward-adaptation and back-adaptation. Data were collected from undergraduate students. The sample size is 105 for Study 1 and 212 for Study 2. Classical item discrimination and difficulty analyses, exploratory factor analysis (EFA), confirmatory factor analysis (CFA), and reliability analysis were performed. Results : A unidimensional structure was found with a high internal consistency (Cronbach's α=0.95) and a high test-retest reliability (r=0.918). In addition, the concurrent validity was examined by correlations of the scale and several other scales measuring constructs related to social appearance anxiety. Conclusion : K-SAAS appears to be a reliable and valid scale for screening and assessing social appearance anxiety.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2020년도 제32회 한글 및 한국어 정보처리 학술대회
• /
• pp.462-467
• /
• 2020

대역사전의 구축은 저자원 언어쌍 간의 기계번역의 품질을 높이는데 있어 중요하다. 대역사전 구축을 위해 기존에 제시된 방법론 중 단어 임베딩을 기반으로 하는 방법론 대부분이 영어-프랑스어와 같이 형태적 및 구문적으로 유사한 언어쌍 사이에서는 높은 성능을 보이지만, 영어-중국어와 같이 유사하지 않은 언어쌍에 대해서는 그렇지 못하다는 사실이 널리 알려져 있다. 본 논문에서는 단어 임베딩을 기반으로 부트스트래핑을 통해 대역사전을 구축하는 방법론을 제안한다. 제안하는 방법론은 소량의 seed 사전으로부터 시작해 반복적인 과정을 통해 대역사전을 자동으로 구축하게 된다. 이후, 본 논문의 방법론을 이용해 한국어-영어 언어쌍에 대한 실험을 진행하고, 기존에 대역사전 구축 용도로 많이 활용되고 있는 도구인 Moses에 사용된 방법론과 F1-Score 성능을 비교한다. 실험 결과, F1-Score가 약 42%p 증가함을 확인할 수 있었으며, 초기에 입력해준 seed 사전 대비 7배 크기의 대역사전을 구축하였다.

• 스마트미디어저널
• /
• 제12권1호
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• 수완나부미
• /
• 제6권1호
• /
• pp.161-191
• /
• 2014

The entry of the logging industry in the once heavily forested riverine middle Agusan Valley where aboriginal Manobos live meant the entry of the material practice of wage labor into this out-of-the-way place. Wage labor converted the once relatively isolated, subsistence animist Manobos into laborers of the expanding capitalist regime. A symptom of modernity, this wage labor also accompanied the coming of Visayan settlers (also loggers paid by wage) who introduced indigenous Manobos the compadrazgo social relationship. This friendly relationship across ethnic identities legitimated social ties and is a social material practice represented in recent bilingual Manobo possession rituals where the Visayan spirit is incarnated along with Manobo spirits. To understand the idea behind spirit embodiment, I explore Manobo ritual as mimesis or poeisis. This representation is shaped by concrete material realities as much as these realities, in turn, are reconfigured by ritual practice. In the older Manobo cosmology, which is based on subsistence economy and dependent on the forest and rivers, individuals have an externalized self (as manifest in the idea of twin soul), in which the inner vital principle is co-extensive with a spirit double in cosmos. Manobos imitate the perceived workings of nature in ritual so as to control them in times of illnesses. In contrast, the mimesis of the Visayan spirit is based on a different political economic set up with its attendant asymmetrical interpersonal relationship. By symbolically representing the Visayan patron as friend, Manobos are able to negotiate the predicament of their subalternity in local modernity.

• 디지털콘텐츠학회 논문지
• /
• 제19권6호
• /
• pp.1161-1167
• /
• 2018

기계 학습의 발전은 인간만이 할 수 있었던 섬세한 작업들을 기계가 할 수 있도록 이끌었고, 이에 따라 많은 기업체들은 기계 학습 기반의 번역기를 출시하였다. 현재 상용화된 번역기들은 우수한 성능을 보이지만 숫자 번역에서 문제가 발생하는 것을 발견했다. 번역기들은번역할문장에 큰숫자가 있을경우종종숫자를잘못번역하며, 같은문장에서숫자만바꿔번역할 때문장의구조를 완전히바꾸어 번역하기도 한다. 이러한 문제점은오번역의 가능성을 높이기 때문에해결해야 될 사안으로여겨진다. 본 논문에서는 Bidirectional RNN (Recurrent Neural Network), LSTM (Long Short Term Memory networks), Attention mechanism을 적용한 Neural Machine Translation 모델을 사용하여 데이터 클렌징, 사전 크기 변경을 통한 모델 최적화를 진행 하였고, 최적화된 모델에 숫자 기호화 알고리즘을 적용하여 상기 문제점을 해결하는 번역 시스템을 구현하였다. 본논문은 데이터 클렌징 방법과 사전 크기 변경, 그리고 숫자 기호화 알고리즘에 대해 서술하였으며, BLEU score (Bilingual Evaluation Understudy score) 를 이용하여 각 모델의 성능을 비교하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권9호
• /
• pp.4651-4654
• /
• 2012

Organized introduction of prophylactic human papillomavirus (HPV) vaccination can reduce the burden of cervical cancer in developing countries. One of the most effective ways is through a national school-based program. Information on teachers is therefore important since this group may have a disproportionate influence in the success of any implementation. Objective: To assess teachers' knowledge and perception of HPV, cervical cancer and HPV vaccine prior to commencing a school-based HPV vaccination program in a multiethnic, predominantly Muslim country. Factors associated with acceptability of the vaccine were identified. Method: A bilingual questionnaire was applied to 1,500 secondary school teachers from 20 urban schools in Malaysia. Data collected were analyzed using SPSS version 17. Results: 1,166 questionnaires were returned. From this group, 46.1% had never heard of HPV while 50.9% had never had a pap smear. However, 73.8% have heard of the HPV vaccine with 75% agreeing to have it. 96% considered themselves religious with 79.8% agreeing to have the vaccine. Conclusions: A national school-based HPV immunization program can be implemented effectively in a multiethnic, cultural and religious country despite limited knowledge of HPV-related pathology among teachers. In addition, the perception that religion has a negative influence on such a program is unwarranted.

• 정보과학회 논문지
• /
• 제44권2호
• /
• pp.163-170
• /
• 2017

통계적 기계 번역을 이용한 구어-수화 번역 연구가 활발해짐에도 불구하고 수화 말뭉치의 자원 희소성 문제는 해결되지 않고 있다. 본 연구는 수화 번역의 첫 번째 단계로써 통계적 기계 번역을 이용한 구어-수지 신호 번역에서 말뭉치 자원 희소성으로부터 기인하는 문제점들을 해결할 수 있는 세 가지 전처리 방법을 제안한다. 본 연구에서 제안하는 방법은 1) 구어 문장의 패러프레이징을 통한 말뭉치 확장 방법, 2) 구어 단어의 표제어화를 통한 개별 어휘 출현 빈도 증가 및 구어 표현의 번역 가능성을 향상시키는 방법, 그리고 3) 수지 표현으로 전사되지 않는 구어의 기능어 제거를 통한 구어-수지 표현 간 문장 성분을 일치시키는 방법이다. 서로 다른 특징을 지닌 영어-미국 수화 병렬 말뭉치들을 이용한 실험에서 각 방법론들이 단독으로 쓰일 때와 조합되어 함께 사용되었을 때 모두 말뭉치의 종류와 관계없이 번역 성능을 개선시킬 수 있다는 것을 확인할 수 있었다.

• 기본간호학회지
• /
• 제24권4호
• /
• pp.296-303
• /
• 2017

Purpose: The purpose of this study was to evaluate the reliability and validity of the Korean version of Diabetes Empowerment Measurement Scale Short Form (DES-SF) for use with diabetic patients in Korea. Methods: A cross-sectional descriptive study was used with 107 participants. Bilingual nursing professionals performed translation and reverse translation. Reliability and validity such as face validity, construct validity, and concurrent validity were conducted. To assess the concurrent validity, the correlation coefficients between the Korean version of the DES-SF and a concurrent scale (Diabetes Self-Efficacy Scale, DSES) were calculated. Results: In the explanatory factor analysis, a uni-dimension was proposed, the one factor accounted for 49.4% of total variances. The Korean version of the DES-SF correlated with a concurrent variable such DSES for reliability of the Korean version of the DES-SF, Cronbach's ${\alpha}=.85$. Conclusion: The findings show that the Korean version of the DES-SF is reliable and valid for evaluating empowerment in patients with diabetes in Korea.

• 한방재활의학과학회지
• /
• 제28권3호
• /
• pp.87-96
• /
• 2018

Objectives The purpose of this study is to provide more whiplash injury-specific measurement tools for Korean patients by measuring the validity and reliability of Korean version of Whiplash Disability Questionnaire (WDQ). Methods Bilingual clinicians translated the original WDQ into Korean. After consensus conference between researchers, it was back-translated into English. The pre-final version was completed and administered to 71 hospitalized patients diagnosed with whiplash injury. Validity was evaluated by concurrent validity. Reliability was assessed using Cronbach's ${\alpha}$ and intraclass correlation coefficient. Results The Korean WDQ showed good reliability with high internal consistency and intra-class correlation coefficient (Cronbach's ${\alpha}=0.96$, intraclass correlation coefficient [ICC]=0.82). Concurrent validity demonstrated positive correlations between Neck Disability Index, 36-Item Short Form Health Survey and WDQ. Conclusions The Korean version of WDQ is a valid and reliable tool for use as a measurement of whiplash injury in Korean patients, and it will be a very useful evaluation tool for both clinicians and researchers.