• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.319-322
• /
• 2021

4차 산업혁명 시대에는 빠른 무선 네트워크와 빅데이터를 기반으로 다양한 기술과 서비스들이 생겨나고 있다. 이런 환경 속에서 우리는 언제 어디서나 스마트폰을 통해 음악을 듣고, 게임을 하며, 웹서핑을 하는 등 PC에 버금가는 다양한 활동을 할 수 있다. 누구든 쉽게 전세계의 웹페이지에 접속하고 SNS를 통해 외국인 친구들과도 쉽게 연락을 할 수 있다. 기계 번역 기술 또한 이렇게 사용자가 늘어나는 만큼 빅데이터를 기반으로 그 정확도가 향상되고 있다. 그러나 일반 명사나 구문과는 다르게 은어, 외래어 등의 사용빈도가 상대적으로 낮은 단어들에 대한 기계 번역 정확도는 여전히 개선이 필요하다. 본 연구에서는 국내에서 가장 많이 사용되는 기계 번역기인 papago 번역기와 Google 번역기의 외래어 인식 정확도에 대한 비교 연구를 진행하였다. 추후, 본 연구 결과를 통해 앞으로의 새로운 연구 방향을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.684-686
• /
• 2022

다양한 언어로 소통하고 있는 우리는 다른 언어와 교류하기 위해 번역, 통역의 존재가 필수가 되기도 한다. 하지만 음성언어를 사용하지 않는 즉, 손으로 언어를 표현하는 수어를 번역하는 통역의 존재는 아직 실현되지 않았다. 이에 본 논문에서는 MediaPipe와 OpenCV 라이브러리를 이용하여 손의 형태를 인식하고 CNN 알고리즘을 통한 텍스트 데이터화 하여 수어 동작을 학습시켜 이를 번역시켜주는 시스템을 연구한다. 이를 통해 공공기관을 이용함에 불편함을 줄이고, 농인의 의사를 보다 빠르게 파악할 수 있도록 도와주는 번역 시스템 제작하는 것에 목적이 있다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.83-92
• /
• 2023

The majority of product users rely on the reviews that are posted on the appropriate website. Both users and the product's manufacturer could benefit from these reviews. Daily, thousands of reviews are submitted; how is it possible to read them all? Sentiment analysis has become a critical field of research as posting reviews become more and more common. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM, CNN, RNN, and GRU. Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. According to experimental results utilizing a publicly accessible dataset with reviews for all of the models, both positive and negative, and CNN, the best model for the dataset was identified in comparison to the other models, with an accuracy rate of 81%.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.3
• /
• pp.183-191
• /
• 2006

As genetic research is getting more active, data construction of genes are needed in the field of biology. Therefore, Gene Ontology Consortium has constructed genetic information by OWL, which is Ontology description language published by W3C. However, previous browsers for Gene Ontology only support simple searching mechanisms based on keyword, tree, and graph, but it is not able to search high quality information considering various relationships. In this paper, we suggest browsing technique which integratesvarious searching methods to support researchers who are doing actually experiment in biology field. Also, instead of typing a query, we propose querv generation technique which constructs query while browsing and query translation technique which translate generated query into SeRQL query It is convenient for user and enables user to obtain high quality information. And by this GO Guide browser, it has been shown that the information of Gene Ontology could be used efficiently.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.29 no.1
• /
• pp.7-13
• /
• 2018

Objectives: Problem behaviors pose a great obstacle to daily functioning in children with neurodevelopmental deficits and are an important target for treatment. In this study, we translated the Behavior Problems Inventory (BPI)-01 into Korean language and tested its psychometric properties. Methods: We attained the approval of the BPI author and performed standard translation-back translation. Then, professional caregivers examined appropriateness according to cultural and situational contexts in order to make necessary modifications of the Korean version of the BPI. Results: The BPI-01, Korea-Scales of Independent Behavior-Revised (K-SIB-R), and Child Behavior Checklist were completed for 98 autistic spectrum disorder or intellectual development disorder participants (mean age=28.3, standard deviation=7.3, range=10.1-51.7). The inter-rater reliability of the BPI-01 was found to be high (r=0.992-1.000). As for the results for concurrent validity for subscale items of BPI-01 and scales of SIB, correlations between SIB and BPI-01 subscales were statistically significant (r=0.357-0.672). Discussion: The Korean version of the BPI-01 showed good psychometric properties with high reliability and sufficient convergent validity. Further examination of the validity of BPI-01 should be carried out with inclusion of younger aged children and a closer look at less frequently occurring symptoms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.8
• /
• pp.1517-1523
• /
• 2016

The global medical tourism industry including Asian market has been activating recently. That is as medical tourists are motivated to seek the higher quality of healthcare with lower costs, as well as of travel. The consumers in this field tend to need customized services of medical tourism. It is needed that the consumers get customized information on medical services and traveling, the clinics and hospitals resolve the issues of offering translation and luring medical tourists from overseas, and the guides, who offer tour and translation service, provide the consumers and the clinics with customized services so that they get the services needed for one another. This research studies the Offline to Online, called O2O, matching platform based on global clinics, which connects medical facilities, patients, and guides for traveling and language services. It presents the customized marketing plans by utilizing customers' experiences from medical services and traveling they use.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.1
• /
• pp.92-99
• /
• 2005

In this paper, we present a high-level design methodology applied on a network system-on-a-chip(SOC) using SystemC. The main target of our approach is to get optimum performance parameters for high network address translation(NAT) throughput. The Fast Ethernet media access controller(MAC) and its direct memory access(DMA) controller are modeled with SystemC in transaction level. They are calibrated through the cycle-based measurement of the operation of the real Verilog register transfer language(RTL). The NAT throughput of the model is within $\pm$10% error compared to the output of the real evaluation board. Simulation speed of the model is more than 100 times laster than the RTL. The validated models are used for intensive architecture exploration to find the performance bottleneck in the NAT router.

• Korean Journal of Cognitive Science
• /
• v.14 no.2
• /
• pp.1-13
• /
• 2003

We introduce a way to generate morphologically and syntactically well-formed English sentences when building Korean to English bilingual dictionary for Machine Translation Systems. It has been proved that basic inflectional or structural descriptions for English sentences are by no means enough to generate proper English sentences because of traditional dictionary structures. Furthermore, much research has been focused only on how to disambiguate semantic ambiguities of words in a bilingual dictionary To take advantage of existing paperback Korean to English bilingual dictionary, its automatic conversion to an electronic version and methodologies to assign proper features to the descriptions for well-formed English sentences with minimum human effort have been proposed on the basis of the dictionary-specific structures. This approach was originally motivated for a glossary-based machine translation system, but it can be also applied to large scale dictionary work.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.6
• /
• pp.746-755
• /
• 2002

EXPRESS is product information description language. It is interpretable by human and software. Product data written in EXPRESS make it possible to exchange between heterogeneous systems. However, the number of software that can use EXPRESS is limited and it is expensive to use the software. XML makes it possible to update and manage data on the Web. Because the Web is easier to use and access than other tools comparatively, data represented by XML need not depend on specific applications or systems and it can be used for exchange of data. Therefore, if we represent EXPRESS-driven data in XML, there will be more active data exchange widely and easily In this work, a method of translation EXPRESS document to XML DTD and XML Schema is proposed. By classification all of EXPRESS syntax element and consideration complex cases caused by this syntax element, a translation rule that represent XML DTD and XML Schema is suggested. Also, a translator which is corresponding to this rule is implemented.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.382-386
• /
• 2004

Recently, with the machine learning trend, most of the machine translation systems on over the world use two syntax tree sets of two relevant languages to learn syntactic tree transfer rules. However, for the English-Vietnamese language pair, this approach is impossible because until now we have not had a Vietnamese syntactic tree set which is correspondent to English one. Building of a very large correspondent Vietnamese syntactic tree set (thousands of trees) requires so much work and take the investment of specialists in linguistics. To take advantage from our available English-Vietnamese Corpus (EVC) which was tagged in word alignment, we choose the SITG (Stochastic Inversion Transduction Grammar) model to construct English- Vietnamese syntactic tree sets automatically. This model is used to parse two languages at the same time and then carry out the syntactic tree transfer. This English-Vietnamese bilingual syntactic tree set is the basic training data to carry out transferring automatically from English syntactic trees to Vietnamese ones by machine learning models. We tested the syntax analysis by comparing over 10,000 sentences in the amount of 500,000 sentences of our English-Vietnamese bilingual corpus and first stage got encouraging result $(analyzed\;about\;80\%)[5].$ We have made use the TBL algorithm (Transformation Based Learning) to carry out automatic transformations from English syntactic trees to Vietnamese ones based on that parallel syntactic tree transfer set[6].