• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.33-39
• /
• 2002

중국어의 품사 태깅(part-of-speech tagging)을 위해서는 중국어 문장들은 내부 단어간의 명확한 분리가 없기 때문에 단어 분할(word segmentation)과 품사 태깅을 동시에 처리해야 한다. 본 논문은 규칙 기반(rule base)과 사전 기반(dictionary base) 기법을 혼합하여 구현한 단어 분할 시스템을 사용하여 입력 문장을 단어 단위로 분할하고, HMM(hidden Markov model) 기반 통계적 품사 태깅 기법을 사용한다. 특히, 본 논문에서는 주어진 말뭉치(corpus)로부터 자동 학습(automatic training)을 통해 품사 사전을 구축하여 구현된 시스템과 말뭉치간의 독립성을 유지한다. 말뭉치는 중국어 간체와 번체 모두를 대상으로 하고, 각 말뭉치로부터 자동 학습을 통해 얻어진 품사 사전으로 단어 분할과 품사 태깅을 한다. 실험결과들은 간체, 번체 각각의 단어 분할 성능과 품사 태깅 성능을 보여준다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.697-698
• /
• 2023

최근 딥 러닝 분야의 기술이 발달하면서 Chat GPT, Google Bard와 같은 자연어 처리 기술이 확대되고 있고 이미지 객체를 분석하는 CLIP, BLIP와 같은 기술도 발전되고 있다. 그러나 전시회와 같은 예술 분야는 딥 러닝 기술 기반의 이미지 데이터 활용이 제한적이다. 본 논문은 전시회장에서의 그림 내부의 객체 데이터를 분석하기 위해 이미지 객체 분석 기술을 사용하고 자연어 처리 기반으로 관람객이 특정 그림에 대한 질문을 입력하면 해당 그림을 식별하는 방법을 제시한다. 이를 통해 관람객이 원하는 그림을 선별하여 관람할 수 있도록 한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.388-392
• /
• 2023

개체 추출은 정보추출의 기초를 구성하는 태스크로, 관계 추출, 이벤트 추출 등 다양한 정보추출 태스크의 기반으로 중요하다. 최근에는 다중 레이블 개체와 중첩 개체를 다루기 위해 스팬기반의 개체추출이 주류로 연구되고 있다. 본 논문에서는 스팬을 표현하는 다양한 매핑과 자질들을 살펴보고 개체추출의 성능에 어떤 영향을 주는지를 분석하여 최적의 매핑 및 자질 조합을 제시하였다. 또한, 모델 구조에 있어서, 사전 학습 언어모델(PLM) 위에 BiLSTM 블록의 추가 여부에 따른 성능 변화를 분석하고, 모델의 학습에 있어서, 미세조정(finetuing) 이전에 예열학습(warmup training)을 사용하는 것이 효과적인지를 실험을 통해 비교 분석하여 제시하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.157-165
• /
• 2021

Recently, studies using deep learning to analyze a large amount of text are being actively conducted. In particular, a pre-trained language model that applies the learning results of a large amount of text to the analysis of a specific domain text is attracting attention. Among various pre-trained language models, BERT(Bidirectional Encoder Representations from Transformers)-based model is the most widely used. Recently, research to improve the performance of analysis is being conducted through further pre-training using BERT's MLM(Masked Language Model). However, the traditional MLM has difficulties in clearly understands the meaning of sentences containing new words such as newly coined words. Therefore, in this study, we newly propose NTM(Newly coined words Target Masking), which performs masking only on new words. As a result of analyzing about 700,000 movie reviews of portal 'N' by applying the proposed methodology, it was confirmed that the proposed NTM showed superior performance in terms of accuracy of sensitivity analysis compared to the existing random masking.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.43-54
• /
• 2024

Recently, there has been a lot of research on utilizing Language Models, and Large Language Models have achieved innovative results in various tasks. However, the practical application faces limitations due to the constrained resources and costs required to utilize Large Language Models. Consequently, there has been recent attention towards methods to effectively utilize models within given resources. Curriculum Learning, a methodology that categorizes training data according to difficulty and learns sequentially, has been attracting attention, but it has the limitation that the method of measuring difficulty is complex or not universal. Therefore, in this study, we propose a methodology based on data heterogeneity-based Curriculum Learning that measures the difficulty of data using reliable prior information and facilitates easy utilization across various tasks. To evaluate the performance of the proposed methodology, experiments were conducted using 5,000 specialized documents in the field of information communication technology and 4,917 documents in the field of healthcare. The results confirm that the proposed methodology outperforms traditional fine-tuning in terms of classification accuracy in both LoRA fine-tuning and full fine-tuning.

• Journal of Agricultural Extension & Community Development
• /
• v.13 no.1
• /
• pp.195-208
• /
• 2006

This study was carried out to analyze the working conditions and Job Satisfaction of foreigner agricultural trainees. Foreigner training program is governmental project to decrease the shortage of labor resources in farm household and increase of income for trainees, to transfer the agricultural technology to sending country. For this purpose, data were gathered from 110 foreigner agricultural trainees consisted of 91 Uzbekistanian and 19 Mongolian by interview with questionnaire. The results are as follows: 1) the trainee answered to increase the income and technical training regardless of nationality, age, wedding, and types of agriculture. 2) the trainee felt crucial difficulties in language usage and homesick during the training program, 3) Training program should be concretized in working schedule.

• Journal of Navigation and Port Research
• /
• v.40 no.5
• /
• pp.249-256
• /
• 2016

The International Association of Marine Aids to Navigation and Lighthouse Authorities(IALA) model course recommends specific aspects of basic curriculums for Vessel Traffic Services(VTS) operator education such as modules, course hours, contents, etc. Most domestic training programs for newly appointed VTS operators comply with such recommendations. The objective of this study is to determine whether such modules for VTS operator training recommended by the current IALA model course correspond to the actual opinions of VTS operators who are currently working in the field. To this end, the relative importance of basic modules for vessel traffic services operator training was analyzed using the Analytic Hierarchy Process(AHP) method. A questionnaire was designed to include 8 modules recommended by the IALA model course, and the survey results of 52 individuals working at 5 VTS centers were analyzed. The result showed that, unlike the assumption by the IALA, domestic VTS operators viewed Nautical Knowledge as the most important modules, followed by Emergency Situations, Traffic Management, Language, Equipment, VHF Radio, Communication Co-ordination, and Personal Attributes, in that order.

• English Language & Literature Teaching
• /
• v.16 no.3
• /
• pp.269-289
• /
• 2010

The present study reports on a study of the development of customized intensive in-service English teachers training programs (IIETTP) reflecting on the demands of elementary/secondary school English teachers. For the purpose of study, a survey was conducted with 1,033 English teachers at elementary/secondary schools across the country. The results showed by and large no significant differences by school level, albeit some slight differences were revealed such as in training times, training methods, the percentages of teaching English in English (TEE), and other things. Since the two IIETTP models are presented as basic formats, they can be modified and applied according to the contexts of schools and the demands of trainees.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.224-226
• /
• 2015

Outwardly, the people in the shipping industry are aware that multicultural working environments and conditions could have a strong influence on the operation of ships. With a lack of cultural awareness and foreign language skill of crew members on ships, there are lots of misunderstandings and miscommunications among (cross-cultural) crews. More and more maritime accidents are caused by human error in the world's oceans. Nevertheless the research on cultural diversity and human interaction on ships is still in its infancy. Due to the rapid change of the demographic make-up of crews, not only teaching and training technical skills for the crews, but also education in nontechnical skills such as cultural awareness, cultural sensitivity, intercultural competence is urgently needed. This study will deal with intercultural issues on ships. It aims to emphasize the necessity of intercultural training in MET.

• International Journal of Advanced Culture Technology
• /
• v.8 no.2
• /
• pp.101-108
• /
• 2020

One difficulty in language learning is the training of reading ability. The improvement on this ability directly affects the process and effect of language learning. At the same time, there are numerous difficulties in actual learning and teaching. Depending on current research, there is two ideas that can utilize to enhance the reading efficiency of learners. One is to amend objective factors; the other is to change subjective factors. Compared with the two ideas, idiosyncratic factors are more manipulable and controllable, so it is more valuable to conduct researches on this. But among the many subjective factors, the degree of their effectiveness is not the same, so this article attempts to compare and analyze the driving effects of two important subjective factors (peer-driven and task-driven) on reading performance. The results show that both factors can have a positive impact on reading comprehension, but different in driving effects. The task-driven has obvious short-term effectiveness; while peer-driven needs to establish its long-term effect on the basis of early coordination and cooperation among team members. Therefore, in order to maximize the achievement of learning, it is necessary to combine strengths and avoid weaknesses according to the characteristics of two factors, so as to help learners improve reading ability most efficiently.