• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.157-161
• /
• 2020

문서 요약(text summarization)은 주어진 문서로부터 중요하고 핵심적인 정보를 포함하는 요약문을 만들어 내는 작업으로, 기계 번역 작업에서 주로 사용되는 Sequence-to-Sequence 모델을 사용한 end-to-end 방식의 생성(abstractive) 요약 모델 연구가 활발히 진행되고 있다. 최근에는 BERT와 MASS 같은 대용량 단일 언어 데이터 기반 사전학습(pre-training) 모델을 이용하여 미세조정(fine-tuning)하는 전이 학습(transfer learning) 방법이 자연어 처리 분야에서 주로 연구되고 있다. 본 논문에서는 MASS 모델에 복사 메커니즘(copying mechanism) 방법을 적용하고, 한국어 언어 생성(language generation)을 위한 사전학습을 수행한 후, 이를 한국어 문서 요약에 적용하였다. 실험 결과, MASS 모델에 복사 메커니즘 방법을 적용한 한국어 문서 요약 모델이 기존 모델들보다 높은 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4244-4274
• /
• 2021

The utilization of UAVs in various fields has led to the development of flying ad hoc network (FANET) technology. In a network environment with highly dynamic topology and frequent link changes, the traditional routing technology of FANET cannot satisfy the new communication demands. Traditional routing algorithm, based on geographic location, can "fall" into a routing hole. In view of this problem, we propose a geolocation routing protocol based on multi-agent reinforcement learning, which decreases the packet loss rate and routing cost of the routing protocol. The protocol views each node as an intelligent agent and evaluates the value of its neighbor nodes through the local information. In the value function, nodes consider information such as link quality, residual energy and queue length, which reduces the possibility of a routing hole. The protocol uses global rewards to enable individual nodes to collaborate in transmitting data. The performance of the protocol is experimentally analyzed for UAVs under extreme conditions such as topology changes and energy constraints. Simulation results show that our proposed QLGR-S protocol has advantages in performance parameters such as throughput, end-to-end delay, and energy consumption compared with the traditional GPSR protocol. QLGR-S provides more reliable connectivity for UAV networking technology, safeguards the communication requirements between UAVs, and further promotes the development of UAV technology.

• International Journal of Contents
• /
• v.4 no.2
• /
• pp.19-23
• /
• 2008

This paper presents a novel method to construct a personalized e-Learning system based on dynamic estimations of item parameters and learners' abilities, where the learning content objects are of the same intrinsic quality or homogeneously distributed and the estimations are carried out using IRT(Item Response Theory). The system dynamically connects the test and the corresponding learning procedures. Test results are directly applied to estimate examinee's ability and are used to modify the item parameters and the difficulties of learning content objects during the learning procedure is being operated. We define the learning unit 'Node' as an amount of learning objects operated so that new parameters can be re-estimated. There are various content objects in a Node and the parameters estimated at the end of current Node are directly applied to the next Node. We offer the most appropriate learning Node for a person's ability throughout the estimation processes of IRT. As a result, this scheme improves learning efficiency in web-base e-Learning environments offering the most appropriate learning objects and items to the individual students according to their estimated abilities. This scheme can be applied to any e-Learning subject having homogeneous learning objects and unidimensional test items. In order to construct the system, we present an operation scenario using the proposed system architecture with the essential databases and agents.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.9 no.6
• /
• pp.71-77
• /
• 1995

This paper deals with design method of learning fuzzy controller for control of an unknown nonlinear plant using the self-tuning algorithm of fuzzy inference rules. In this method the fuzzy identification model obtained that the joined identification model of nonlinear part and linear identification model of linear part by fuzzy inference systems. This fuzzy identification model ordered self-tuning by Decent method so as to be servile to nonlinear plant. A the end, designed learning fuzzy controller of fuzzy identification model have learning structure to model reference adaptive system. The simulation results show that th suggested identification and learning control schemes are practically feasible and effective.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.529-534
• /
• 2020

인공신경망 기반 기계번역(Neural Machine Translation, NMT)이란 딥러닝(Deep learning)을 이용하여 출발 언어의 문장을 도착 언어 문장으로 번역해주는 시스템을 일컫는다. NMT는 종단간 학습(end-to-end learning)을 이용하여 기존 기계번역 방법론의 성능을 앞지르며 기계번역의 주요 방법론으로 자리잡게 됐다. 이러한 발전에도 불구하고 여전히 개체(entity), 또는 전문 용어(terminological expressions)의 번역은 미해결 과제로 남아있다. 개체나 전문 용어는 대부분 명사로 구성되는데 문장 내 명사는 주체, 객체 등의 역할을 하는 중요한 요소이므로 이들의 정확한 번역이 문장 전체의 번역 성능 향상으로 이어질 수 있다. 따라서 본 논문에서는 지식그래프(Knowledge Graph)를 이용하여 심볼릭 지식을 NMT와 결합한 뉴럴심볼릭 방법론을 제안한다. 또한 지식그래프를 활용하여 NMT의 성능을 높인 선행 연구 방법론을 한영 기계번역에 이용할 수 있도록 구조를 설계한다.

• Educational Technology International
• /
• v.6 no.1
• /
• pp.81-101
• /
• 2005

Campus-based universities have provided face-to-face instruction traditionally. But recently, it is becoming a trend that they provide blended learning which combines e-learning and f2f instruction. Therefore, traditional university has been installing the ICT related convenience for the faculty and students to use easily to their classes. The purpose of this study is to develop quality indicators of ICT-related support for proper blended learning in traditional campus-based universities. This indicators are used for measuring the quality of ICT-related services at university level for quality education. To this end, first, we reviewed literature about quality indicators of university evaluation and e-learning. Second,we did case study. We selected and analyzed one university for a case, And we identified what elements are perceived important to faculty for more efficient use of technology to their class. Third, we summarized all this data and established the quality indicators framework of ICT-related components for blended learning in campus-based universities. Then, these indicators were revised after the expert evaluation. And then 10 experts and practitioners scored importance rating. Finally, we sum them up to 17 indicators and 48 sub-indicators in three phases (input, process, output). Among them, e-learning related organization or body, usability of Learning Management System, and quality assessment system got the highest scores. These indicators are supposed to contribute to measure the quality of ICT-related environment for blended learning and to provide informations about what is required for efficient blended learning in the campus-based universities.

• English Language & Literature Teaching
• /
• v.8 no.1
• /
• pp.39-53
• /
• 2002

Recently much research has investigated the role of attention in L2 learning, comparing the effects of explicit learning with those of implicit learning. With this background the research aims at examining the effects explicit focus on form has on L2 learning based on the acquisition of the English article system. The participants were 70 Korean college students who enrolled in English Composition classes. The experimental group received explicit focus on form including grammatical explanation, input enhancement, output practice, and negative evidence (corrective feedback) for two weeks, while the control group was exposed to sufficient input and negative evidence. Completion tasks were administered at the beginning and the end of the semester. In addition, errors in the use of English articles were analysed on their compositions both before and after the different treatments. The analyses of the results show that the explicit focus on form group improved significantly more than the control group, particularly for the definite article 'the', and some changes occurred in the distribution of article errors. These findings suggest that explicit teaching plays a more contributory role than implicit teaching in acquiring L2 knowledge in classroom-based L2 learning.

• Korean Journal of Child Studies
• /
• v.27 no.6
• /
• pp.183-197
• /
• 2006

The purpose of this study was to explore the relationships between learning-related social skills, early school adjustment, and academic achievement. The sample consisted of 160 first grade children in one elementary school in the city of Ilsan. The teacher rated children's learning-related social skills and early school adjustment. Academic achievement was assessed by scores on Korean language arts and math exams administered at the end of first semester. Learning-related social skills and early school adjustment were correlated with the children's academic achievement. Particularly, the cooperation and mastery behavior of learning-related social skills were strongly associated with the early school adjustment and academic achievement.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.93-110
• /
• 2023

Recently, attempts have been made to convert unstructured text into vectors and to analyze vast amounts of natural language for various purposes. In particular, the demand for analyzing texts in specialized domains is rapidly increasing. Therefore, studies are being conducted to analyze specialized and general-purpose documents simultaneously. To analyze specific terms with general terms, it is necessary to align the embedding space of the specific terms with the embedding space of the general terms. So far, attempts have been made to align the embedding of specific terms into the embedding space of general terms through a transformation matrix or mapping function. However, the linear transformation based on the transformation matrix showed a limitation in that it only works well in a local range. To overcome this limitation, various types of nonlinear vector alignment methods have been recently proposed. We propose a vector alignment model that matches the embedding space of specific terms to the embedding space of general terms through end-to-end learning that simultaneously learns the autoencoder and regression model. As a result of experiments with R&D documents in the "Healthcare" field, we confirmed the proposed methodology showed superior performance in terms of accuracy compared to the traditional model.