• 한국IT서비스학회지
• /
• 제21권2호
• /
• pp.85-95
• /
• 2022

This study analyzed the translation error factors of machine translation services such as Naver Papago and Google Translate through Self-Attention path visualization. Self-Attention is a key method of the Transformer and BERT NLP models and recently widely used in machine translation. We propose a method to explain translation error factors of machine translation algorithms by comparison the Self-Attention paths between ST(source text) and ST'(transformed ST) of which meaning is not changed, but the translation output is more accurate. Through this method, it is possible to gain explainability to analyze a machine translation algorithm's inside process, which is invisible like a black box. In our experiment, it was possible to explore the factors that caused translation errors by analyzing the difference in key word's attention path. The study used the XLM-RoBERTa multilingual NLP model provided by exBERT for Self-Attention visualization, and it was applied to two examples of Korean-Chinese and Korean-English translations.

• Journal of Multimedia Information System
• /
• 제8권4호
• /
• pp.221-232
• /
• 2021

One bottleneck of Bengali to Hindi transfer based machine translation system is the translation of suffixes of noun. The appropriate translation of a nominal suffix often depends on the semantic role of the corresponding noun chunk in the sentence. With the availability of a high performance Bengali morphological analyzer and a basic Bengali parser it is possible to identify the role of each noun chunk. This information may be used for building rules for translating the ambiguous nominal suffixes. As there are some similarities between the uses of Bengali and Hindi nominal suffixes we find that the rules may be identified by linguistically analyzing corpus data. In this paper, we identify rules for the ambiguous four Bengali nominal suffixes from corpus data and evaluate their performances. This set of rules is able to resolve a majority of the nominal suffix ambiguities in Bengali to Hindi transfer based machine translation system. Using the rules, we are able to translate 98.17% Bengali nouns correctly which is much better than the baseline ILMT system's accuracy of 62.8%.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.899-904
• /
• 2001

The impact of PVD coatings can be summed up in practical terms: this technology historically complements the best designed tool substrates to enhance cutting performance. PVD coatings are now incorporated in 25% of all HSS tools. The functionality is to extend the machining speed range, improve wear resistance at the cutting edge, and reduce friction at chip/tool contact areas to allow easier chip evacuation. These translate to a larger safe zone, as discussed in the failure mode diagram, for better productivity and higher reliability in machining operations of the customer. PVD coatings therefore represent an enabling technology that extends the application range of cutting tools in response to modern industrial needs. PVD coatings prolong the product life cycle of HSS tools and help this "mature" material to hold its territory against the advent of the newer hardmetal and ceramic tool materials. There is a lot of competitive life left particularly in PVD coated HSS endmills, drills, threading/tapping tools. PM HSS technology further increases the possibilities.ibilities.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.239-240
• /
• 2009

We live in a flat world in which globalization fosters communication, travel, and trade among more than 150 countries and thousands of languages. To surmount the barriers among these languages, translation is required; Speech-to-Speech translation will automate the process. Thanks to recent advances in Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-Speech (TTS), one can now utilize a system to translate a speech of source language to a speech of target language and vice versa in affordable manner. The three phase process establishes that the source speech be transcribed into a (set of) text of the source language (ASR) before the source text is translated into the target text (MT). Finally, the target speech is synthesized from the target text (TTS).

• 한국항만학회지
• /
• 제6권2호
• /
• pp.3-24
• /
• 1992

In the fuzzy control of shop the qualitative knowledge and information that the ship's operators have acquired through their experience can be logically described by the Linguistic control Rule (LCR). The algorithm of the control is made of the LCR and the control of the shop is performed by processing this algorithm implementing a computer. The problem in the fuzzy control is that it is very difficult to describe qualitative human knowledge in the LCR correctly. To tackle this difficulty a Fuzzy Neural Network (FNN) was introduced in this paper. The characteristics of the multi-layer FNN control system applied to the ship's steering system is investigated through the computer simulation, and the results were compared with those of the ordinary fuzzy control system of a ship. The results showed that the FNN method is a very effective to translate human knowledge into the LCR.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.689-692
• /
• 2020

People have studied English using online English dictionaries when they looked for the meaning of English words or the example sentences. These days, as the AI technologies such as machine learning have been developing, documents can be translated in real time with Kakao, Papago, Google translators and so on. But, there has still been some problems with the accuracy of translation. The AI secretaries can be used for real-time interpreting, so this kind of systems are being used to translate such the web pages, papers into Korean. In this paper, we researched on the usage frequency of the combined English phrases from dictionaries by analyzing the number of the searched results on Google. With the result of this paper, we expect to help the people to use more English fluently.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.25-30
• /
• 2024

Various new technologies and aiding instruments are always being introduced for the betterment of the challenged. This project focuses on aiding the mute in expressing their views and ideas in a much efficient and effective manner thereby creating their own place in this world. The proposed system focuses on using various gestures traced into texts which could in turn be transformed into speech. The gesture identification and mapping is performed by the Kinect device, which is found to cost effective and reliable. A suitable text to speech convertor is used to translate the texts generated from Kinect into a speech. The proposed system though cannot be applied to man-to-man conversation owing to the hardware complexities, but could find itself very much of use under addressing environments such as auditoriums, classrooms, etc

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제30권1호
• /
• pp.27-36
• /
• 2024

Purpose: The role and facilities of public health centers responsible for local health are becoming increasingly important due to recurring infectious diseases such as COVID-19. With sudden outbreaks of infectious diseases, the infrastructure of public health center facilities like screening clinics are constructed varies depending on local conditions. resulting in discrepancies between intended usage and actual usage. Establishing guidelines for infectious disease response facilities that can be efficiently used within local communities is necessary. Methods: Field surveys are conducted at 6 public health centers to gather insights into the essential rooms, circulation patterns, and key considerations for space planning in screening clinics. Results: Ten design considerations emerge from the data, including spatial requirements, circulation guidelines, and considerations for accommodating diverse user needs and local conditions. Implications: Further research is needed to translate these guidelines into prototypes of temporary facilities.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.345-348
• /
• 2008

최근 용접공정은 무인화 및 자동화 시스템의 구축이 급속하게 발전하고 있으며 정확한 용접현상의 해석을 위하여 여러 가지 신호처리 알고리즘을 적용하고 있다. 본 논문에서는 아크용접의 모니터링시스템의 구성에 있어서 용접 품질을 실시간으로 판단할 수 있는 효율적인 신경회로망을 제시하고, 학습 데이터의 선정을 위한 전처리 과정을 제시하며, 학습된 신경회로망을 이용하여 실제 용접이 이루어지는 파형에 대한 평가를 보다 정밀하고 정확하게 평가 할 수 있는 방법을 제시한다.

• 한국의류학회지
• /
• 제24권5호
• /
• pp.714-723
• /
• 2000

The purpose of this study is to develop functional and sensible brassiere for middle-aged women. As a methodology, engineering design process, especially, QFD(Quality Function Deployment) was adopted to translate consumer's needs into product design parameters. Wearing tests of commercial brassiere were performed for the development o subjective measurement scale. The environmental condition was controlled at 28$\pm$1$^{\circ}C$, 65$\pm$3%RH. As results, subjective measurement scale and dimension for the evaluation of sensible brassiere were extracted from factor analysis. Four factors were fitting, aesthetic property, pressure sensation, displacement of brassiere due to movement. Regression equations with the subjective evaluation descriptors were developed for the prediction of wearing comfort of brassiere. (R2=.82) The most critical design parameter was wire-related property and second one was stretchability of main material of brassiere. Also, wearing comfort of brassiere was affected by the interaction of initial stretchability of wing and support of strap.