• Physical Therapy Korea
• /
• v.25 no.1
• /
• pp.53-61
• /
• 2018

Background: The process of language translation, adaptation, and cross-cultural validation of tools for use in multiple countries requires the adoption of well-established, comprehensive, and rigorous methodological approaches. Back translation, which is the most recommended method, permits the detection of errors in the translation and the identification of words or phrases that cannot be accurately or literally translated. Objects: The aim of this study was to verify the content validity of a Korean version of a Balance Evaluation Systems test (BESTest) by using a back-translation method. Methods: This research was conducted in six steps: 1) translation of the BESTest into Korean, 2) evaluation of the translation conformity of Korean-translated BESTest, 3) evaluation of the degree of translation comprehension, 4) back translation of Korean BESTest, 5) evaluation of the technical and conceptual equivalence, and 6) completion of the Korean version of BESTest by the translation verification committee. Results: In this study, Korean version of the BESTest achieved a rating of more than 3 (moderate) for translation comprehension, and technical equivalence and conceptual equivalence of back translation were evaluated as 3 (moderate) or more. Conclusion: The Korean version of the BESTest has proven content validity and is an appropriate tool to measure balance function.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.258-261
• /
• 2019

딥러닝을 이용한 Sequence to Sequence 모델의 등장과 Multi head Attention을 이용한 Transformer의 등장으로 기계번역에 많은 발전이 있었다. Transformer와 같은 성능이 좋은 모델들은 대량의 병렬 코퍼스를 가지고 학습을 진행하였는데 대량의 병렬 코퍼스를 구축하는 것은 시간과 비용이 많이 드는 작업이다. 이러한 단점을 극복하기 위하여 합성 코퍼스를 만드는 기법들이 연구되고 있으며 대표적으로 Back Translation 기법이 존재한다. Back Translation을 이용할 시 단일 언어 데이터를 가상 병렬 데이터로 변환하여 학습데이터의 양을 증가 시킨다. 즉 말뭉치 확장기법의 일종이다. 본 논문은 Back Translation 뿐만 아니라 Copied Translation 방식을 통한 다양한 실험을 통하여 데이터 증강기법이 기계번역 성능에 미치는 영향에 대해서 살펴본다. 실험결과 Back Translation과 Copied Translation과 같은 데이터 증강기법이 기계번역 성능향상에 도움을 줌을 확인 할 수 있었으며 Batch를 구성할 때 상대적 가중치를 두는 것이 성능향상에 도움이 됨을 알 수 있었다.

• Physical Therapy Korea
• /
• v.22 no.4
• /
• pp.51-61
• /
• 2015

The purpose of this study were to translate the Fullerton Advanced Balance (FAB) scale into Korean and to verify the content validity by utilizing a back-translation method with a view to assessing balance function and the risk of falling in a clinical research setting. This research was conducted in six steps. First, three Korean physical therapists translated the FAB scale into Korean. Second, two bilingual professors of physical therapy and a physical therapist evaluated translation conformity of Korean-translated FAB scale. In the third and fourth steps, twelve physical therapists evaluated the degree of translation comprehension, and a translator back-translated the Korean FAB scale into the original language. Fifth, a bilingual professor of physical therapy and two native speakers evaluated the technical and conceptual equivalence between the original and translation versions. In this process, inappropriate translated items were revised using recommended substitute words or sentences, and all items were evaluated on the basis of three points or more on a rating scale in terms of translation comprehension, and the technical and conceptual equivalence of the back-translation. In the sixth and last step, the translation verification committee completed the final Korean version. The above process indicated that the content validity of the Korean-translated FAB scale was established by means of systematic translation methods, and it can therefore be used to assess balance function and the risk of falls in a clinical research setting.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.11 no.2
• /
• pp.45-56
• /
• 2016

Objectives : The aim of this study is to verify if the translation of chronic low back pain questionary is done properly. Methods : We used pattern identification of chronic low back pain in the guideline suggested by Ministry of Food and Drug Safety when making the questionnaire. And we used expressions which four native korean speakers who have bachelor's degree on chinese and teach related subjects in university have agreed on for two times. Results : We examined translated sentences about 40 symptoms according to 9 large categories on the questionnaire and corrected them into agreed expressions. Conclusions : In this study, we carried out evaluations on the suitability of the translations of categories which identify symptoms of low back pain. From now on, it is necessary to verify the degree of accuracy of question items that have been subjected to translation verification in clinical diagnosis. Furthermore considering the characteristics of patients with low back pain, we think diagnostic tools which reflects objective diagnosis results other than diagnostic identification are needed in the clinical field.

• The korean journal of orthodontics
• /
• v.28 no.1 s.66
• /
• pp.61-74
• /
• 1998

The Purpose of this study was to investigate the stress distribution and tooth displacement at the initial phase produced by 5 types of molar uprighting springs using finite element method. The three dimensional finite element model of lower dentition, bone and springs was composed of 5083 elements and 2071 nodes. The results were as follows: 1. In case of helical spring and root spring, intrusion of lower canine and first premolar were observed md distal tipping, translation and extrusion of lower second molar were observed. 2. In case of T-loop, modified T-loop and box loop, intrusion and distal translation of lower second premolar were observed, and the largest crown distal tipping and translation of lower second molar were observed in T-loop and the smallest were observed in box loop. 3. In case of T-loop with cinch-bact crown distal tipping and translation of lower second molar were decreased, but extrusion was also decreased. 4. With increase of activation in T-loop, mesial translation and won distal tipping of lower second molar were increased and edentulous space was closing, but distal translation of second premolar was also increased. 5. With increase of tip-back bend in T--loop, distal tipping and translation of lower second molar were increased, but extrusion was also increased more largely.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.470-473
• /
• 2018

최근 제안된 순환 신경망 기반 Encoder-Decoder 모델은 기계번역에서 좋은 성능을 보인다. 하지만 이는 대량의 병렬 코퍼스를 전제로 하며 병렬 코퍼스가 소량일 경우 데이터 희소성 문제가 발생하며 번역의 품질은 다소 제한적이다. 본 논문에서는 기계번역의 이러한 문제를 해결하기 위하여 단일-언어(Monolingual) 데이터를 학습과정에 사용하였다. 즉, 역-번역(Back-translation)을 이용하여 단일-언어 데이터를 가상 병렬(Pseudo Parallel) 데이터로 변환하는 방식으로 기존 병렬 코퍼스를 확장하여 번역 모델을 학습시켰다. 역-번역 방법을 이용하여 영-한 번역 실험을 수행한 결과 +0.48 BLEU 점수의 성능 향상을 보였다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.239-244
• /
• 2022

Neural Machine Translation (NMT) is gradually breaking down the boundary between human and machine translation. We look at actual cases of human and machine translation and discuss why machine translation needs a human touch. In this paper, we raise three driving questions: Can humans be replaced by machines?; How human translators can remain successful in a NMT-driven world?; Is it possible to eliminate language barrier in the era of NMT and World Englishes? The answers to these questions are all negative. We suggest that machine translation is a useful tool with rapidity, accuracy, and low cost productivity. However, the machine translation is limited in the areas of culture, borrowing, ambiguity, new words and (national) dialects. The machines cannot imitate the emotional and intellectual abilities of human translators since machines are based on machine learning, while humans are on intuition. The machine translation will be a useful tool that does not cause moral problems when using methods such as back translation and human post-editing. To conclude, we propose the blended approach that machine translation cannot be completed without the touch of human translation.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.229-236
• /
• 2011

In this paper we present light weighted English-to-Korean and Korean-to-English mobile translators on smart phones. For natural translation and higher translation quality, translation engines are hybridized with Translation Memory (TM) and Rule-based translation engine. In order to maximize the usability of the system, we combined an Optical Character Recognition (OCR) engine and Text-to-Speech (TTS) engine as a Front-End and Back-end of the mobile translators. With the BLEU and NIST evaluation metrics, the experimental results show our E-K and K-E mobile translation equality reach 72.4% and 77.7% of Google translators, respectively. This shows the quality of our mobile translators almost reaches the that of server-based machine translation to show its commercial usefulness.

• Journal of Korean Academy of Nursing Administration
• /
• v.13 no.4
• /
• pp.509-515
• /
• 2007

Purpose: The purpose of this study was to translate and validate the Korean version of Hall's Professional Inventory(HPI) scale to assess levels of professionalism among Korean registered nurses. Method: The 25 item HPI scale was translated and content review was done by translation panel. After the content review, a bilingual nursing scholar performed the back-translation into English. A semantic equivalence test was conducted with 5 American nursing professors. A pilot study was conducted with a sample of 164 registered nurses in Korea to test the validity and reliability of the translated HPI. Result: The content equivalence for translated version of HPI was validated by a translation panel. The finding of the semantic equivalence test of back-translated version was 72.8%. The Cronbach's alpha for the Korean version of HPI was .820. Conclusions: This study provides information about the issues of translating an instrument such as the HPI. The Korean version of the HPI is a valid and reliable instrument and can have psychometric properties equivalent to those of the original HPI. The translated version could be used for assessing levels of professionalism for other health care professionalism as well as nurses.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.22 no.1
• /
• pp.33-44
• /
• 2018

Objectives This study aimed to perform a cross-cultural translation of 5 kinds of pattern identification questionnaires from Korean to English: questionnaires for seven emotions, fatigue and malaise, phlegm, food retention, and blood stasis. Methods We followed the strict guideline on the cross-cultural translation of healthcare evaluation tool. Total five stages of study were conducted. First, translations of two individual translators. Second, synthesizing of the two results. Third, two back translations from synthesized version to Korean. Fourth, expert committee reviewed with the original version, synthesized version, back translated versions to make a pre-final version. Last, with the pre-final version, 5 Americans evaluated face validity of the pre-final version. We made a final version after the above-mentioned 5 stages. Result and conclusion International versions of the 5 kinds of pattern identification questionnaires were completed. We can expect this versions are widly used for clinical usage and following academical researches.