• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.2
• /
• pp.172-178
• /
• 2015

Constructing a bilingual multi-word lexicon is confronted with many difficulties such as an absence of a commonly accepted gold-standard dataset. Besides, in fact, there is no everybody's definition of what a multi-word unit is. In considering these problems, this paper evaluates and analyzes the context vector approach which is one of a novel alignment method of constructing bilingual lexicons from parallel corpora, by comparing with one of general methods. The approach builds context vectors for both source and target single-word units from two parallel corpora. To adapt the approach to multi-word units, we identify all multi-word candidates (namely noun phrases in this work) first, and then concatenate them into single-word units. As a result, therefore, we can use the context vector approach to satisfy our need for multi-word units. In our experimental results, the context vector approach has shown stronger performance over the other approach. The contribution of the paper is analyzing the various types of errors for the experimental results. For the future works, we will study the similarity measure that not only covers a multi-word unit itself but also covers its constituents.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.244-251
• /
• 2009

We present a transformation which converts open-code multi-staged programs into closed ones. Staged computation, which explicitly divides a computation into separate stages, is a unifying framework for existing program generation systems. Because a multi-staged program generates another program, which can also generate a third program and on, the implementation of a multi-staged language is not straightforward. Dynamic binding of (lexically free) variables in code also makes the implementation of a multi-staged language hard. By converting each code into code of function which takes environment for free variables as its argument and giving an actual environment at the code-composition site, we can transform a open-code program into a closed-code one. Combining with Davies and Pfenning's method, our closed-code-conversion enables the implementation of the unstaged language to be useful for executing multi-staged programs. We also prove the correctness of our conversion: the converted program is equivalent to the original program, and the converted program does not have open code.

• Journal of The Korean Association of Information Education
• /
• v.3 no.2
• /
• pp.41-53
• /
• 2000

The purpose of the paper is communication between multi-agents for student's learning at web based collaborative learning. First, this study investigated the whole contents and characteristics of an agent system and discussed KQML, communication language between multi-agents. Also, we suggested architecture of an agent based system for collaborative learning and interaction method between agents using KQML. We design어 and implemented collaborative learning system using Java programming language, and we also demonstrate the efficiency of collaborative learning system by communication between multi-agents through experiments.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.661-664
• /
• 2018

온라인 게시판 글과 채팅창에서 주고받는 대화는 실제 사용되고 있는 구어체 특성이 잘 반영된 텍스트 코퍼스로 음성인식의 언어 모델 재료로 활용하기 좋은 학습 데이터이다. 하지만 온라인 특성상 노이즈가 많이 포함되어 있기 때문에 학습에 직접 활용하기가 어렵다. 본 논문에서는 사용자 입력오류가 다수 포함된 문장에서의 한글 오류 보정을 위한 sequence-to-sequence Denoising Autoencoder 모델을 제안한다.

• Journal of Korean Academic Society of Home Health Care Nursing
• /
• v.23 no.1
• /
• pp.5-15
• /
• 2016

Purpose: This study was conducted to evaluate health service delivery and attitudes, toward multi-cultural clients amongst community health practitioners (CHPs). Methods: A survey was conducted among 242 CHPs from December 10-22, 2015. The collected data were analyzed using chi-square test, t-test, and ANOVA using SPSS 18.0. Results: General awareness of multi-culturalism varied significantly by CHPs age and language ability. Additionally, utilization of services in accordance with the location of community health centers (CHCs) was significantly higher in rural areas than urban areas CHCs in post-partum maternal & neonate care giver service (in maternal child health), management of health educational programs and management of physical exercise (in implementing healthy life style) and networking resources in & outside of CHCs (in management of chronic disease). Conclusion: CHPs deliver health-care services to multi-cultural clients, but have not received sufficient training or education to serve these clients effectively. CHPs who received multi-cultural and foreign language training had more positive experiences with multi-cultural clients. This supports the needs for developing educational programs to enhance multi-cultural understanding amongst CHPs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.9
• /
• pp.1089-1094
• /
• 2004

Agents in Mlulti-Agent Systems (MAS) should make use of a common Agent Communication Language (ACL) in order to negotiate with others, and conform to negotiation protocols that are designed to reach agreements. Therefore, agents must have suitable architectures that could cover above requirements. In this paper, we define an instructive ACL and compare it with other ACLs such as Foundation for Intelligent Physical Agents(FIPA) ACL and Knowledge Query Manipulation Language (KQML). In particular, we represent agents as logic programs with beliefs, desires, intentions and negotiation library. Finally, we show how the planner, which is in the negotiation library, provides plans of actions and updates agent's beliefs.

• Journal of Internet Computing and Services
• /
• v.8 no.1
• /
• pp.115-123
• /
• 2007

Agents in Multi-Agent System; (MAS) should make use of a common Agent Communication Language (ACL) in order to negotiate with others, and conform to negotiation protocols thatare designed to reach agreements. Therefore, agents must have suitable architectures that could cover above requirements. In this paper, we define an instructive ACL and compare it with other ACLs such as Foundation for Intelligent Physical Agents (FIPA) ACL and Knowledge Query Manipulation Language(KQML), In particular, we represent agents as logic programs with knowledge base and negotiation library. Finally, we show how the planner, which is in the negotiation library, provides the plan of actions and updates agent's knowledge base.

• Journal of Information Technology Applications and Management
• /
• v.21 no.3
• /
• pp.65-77
• /
• 2014

Ubiquitous learning has aroused great interest and is becoming a new way for foreign language education in today's society. However, how to increase the learners' initiative and their community cohesion is still an issue that deserves more profound research and studies. Emotional intelligence can help to detect the learner's emotional reactions online, and therefore stimulate his interest and the willingness to participate by adjusting teaching skills and creating fun experiences in learning. This is, actually the new concept of smart education. Based on the previous research, this paper concluded a neural mechanism model for analyzing the learners' emotional characteristics in ubiquitous environment, and discussed the intelligent monitoring and automatic recognition of emotions from the learners' speech signals as well as their behavior data by multi-agent system. Finally, a framework of emotional intelligence system was proposed concerning the smart foreign language education in ubiquitous learning.