• Journal of Korean Society of Archives and Records Management
• /
• v.20 no.4
• /
• pp.1-17
• /
• 2020

Along with the development of information technology, the digitalization of archives has also been accelerating. However, digital archives have limitations in effectively searching, interlinking, and understanding records. In response to these issues, this study proposes a knowledge graph that represents comprehensive relationships among heterogeneous entities in digital archives. In this case, the knowledge graph organizes resources in the archives on the Korean financial crisis of 1997 by transforming them into named entities that can be discovered by machines. In particular, the study investigates and creates an overview of the characteristics of the archives on the Korean financial crisis as a digital archive. All resources on the archives are described as entities that have relationships with other entities using semantic vocabularies, such as Records in Contexts-Ontology (RiC-O). Moreover, the knowledge graph of the Korean Financial Crisis of 1997 is represented by resource description framework (RDF) vocabularies, a machine-readable format. Compared to conventional digital archives, the knowledge graph enables users to retrieve a specific entity with its semantic information and discover its relationships with other entities. As a result, the knowledge graph can be used for semantic search and various intelligent services.

• Journal of Elementary Mathematics Education in Korea
• /
• v.12 no.1
• /
• pp.1-25
• /
• 2008

The purpose of this study was to identify pre-service teachers' Pedagogical Content Knowledge (PCK) about decimal calculation. A written questionnaire was developed dealing with decimal calculation. A total of 152 pre-service teachers from 3 universities were selected for this study; they had taken an elementary mathematics teaching method course and had no teaching experience. The results were as follows: First, with regard to the method of decimal calculation, most pre-service teachers were familiar with algorithms introduced in the textbook. But with regard to the meaning of decimal calculations, they had difficulties in understanding decimal multiplication or decimal division with decimal number. Second, pre-service teachers recognized reasons of errors as well as errors patterns that student might make. But this recognition was limited mainly to errors related to natural number calculation. Third, pre-service teachers frequently commented about decimals algorithms, picture models, the meanings of decimal calculations, and connections to natural number calculations. Many of them represented the meanings of decimal calculations through picture models as to help students' understanding, while they just mentioned algorithms or treated decimal calculation as natural number calculations with decimal point.

• Knowledge Management Research
• /
• v.25 no.3
• /
• pp.99-119
• /
• 2024

This research aims to develop high-quality generative AI services by overcoming the limitations of existing Retrieval-Augmented Generation (RAG) models and implementing an enhanced graph-based RAG system to improve knowledge-based question answering (QA) systems. While traditional RAG models demonstrate high accuracy and fluency by utilizing retrieved information, their accuracy can be compromised due to the use of pre-loaded knowledge without rework. Additionally, the inability to incorporate real-time data after the RAG configuration leads to a lack of contextual understanding and potential biased information. To address these limitations, this study implements an enhanced RAG system utilizing graph technology. This system is designed to efficiently search and utilize information. In particular, LangGraph is employed to evaluate the reliability of retrieved information and to generate more accurate and improved answers by integrating various information. Furthermore, the specific operation method, key implementation steps, and case studies are presented with implementation code and verification results to enhance understanding of Advanced RAG technology. This research provides practical guidelines for actively implementing enterprise services utilizing Advanced RAG, making it significant.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.1363-1373
• /
• 2009

본 연구는 두 집단지성의 가장 대표적인 서비스인 네이버 지식iN과 위키피디아의 구조적, 경험적 차이를 바탕으로 생산의 차원에서 생산 주기, 생산 참여자, 생산물의 모델을 설정하고, 새롭게 탄생하는 지식을 중심으로 검증함으로써 최종 지식 소비 행위를 반영한 각각의 종합모델을 도출하였다. 우리는 웹에서 집단지성의 일상화를 확인할 수 있다. 지식 획득 매체가 매스미디어에서 인터넷으로 변화하는 과정에서 등장한 포털 및 검색사이트는 지식의 생산이 전문가패러다임에서 소비자 중심으로 재편될 수 있는 가능성을 열어주었다. 그리고 이러한 생산 방식의 변화는 '지식'의 개념 역시 변화시키고 있다. 즉, 집단지성이라는 새로운 웹2.0의 현상이 지식생산방식을 변화시키고 변화된 지식생산방식은 '지식'자체를 변화시킨다는 이론적 가설을 도출할 수 있는 것이다. 본 연구는 이러한 새로운 현상들을 분석하기 위해서는 먼저 보다 엄밀하게 집단지성의 개념을 규정할 필요성에 출발하였다. 현재 집단지성이라는 이름으로 불리면서 급격히 성장하고 있는 위키 방식의 인터넷 서비스와 지식검색 방식의 인터넷 서비스를 비교함으로써 보다 정교한 집단지성의 모델을 구축하고자 하였다. 위키형 집단지성과 지식검색형 집단지성의 차이점은 경험적으로도 뚜렷하게 확인할 수 있다. 본 연구는 이러한 경험적 차이와 기존의 문헌에서 밝혀진 사실들을 바탕으로 두 서비스의 지식생산 방식을 생산플로우, 생산참여자 성향, 생산물(지식)의 성향과 같이 세 영역으로 나누어 각각의 가설 모델을 설정하고 이 모델을 선정된 질의어를 바탕으로 검증한 뒤에 최종적인 모델을 도출하는 방식으로 진행되었다. 지식검색형 집단지성은 '질문-답변-채택'의 구조이고, 그 구조 속에서 '질문기-답변기-순서화기'를 거쳐 하나의 지식 덩어리인 'K-let'을 생산한다. 생산된 'K-let'들은 지식검색서비스의 데이터베이스에 축적되고, 이는 공통된 질의어를 기준으로 소비자들에 의해서 검색되어 소비된다. 하나의 질문에 대해 여러 개의 답변들이 존재하고, 답변자의 성향은 크게 전문성과 체계성을 바탕으로 한 전문가형 답변자와 경험적이고 의견지향적인 대화형 답변자로 나눠진다. 다수의 네티즌들의 참여에 의해서 지식의 생산이 진행되므로 질문의 성향 역시 사실, 의견, 경험 등 다양한 스펙트럼을 가지는 모델로 설정하였다. 반면에 위키형 집단지성은 개방형 플랫폼을 바탕으로 한 백과사전의 형식이며, 이러한 형식 속에서 최초의 개념어 등록과 다수의 편집활동을 거치면서 완성되지 않는 하나의 아티클인 'W-let'을 생산한다. 이러한 'W-let'은 생성 초기에 소수에 의한 활발한 내용 입력 활동으로 어느 정도의 안정화를 거친 후에는 꾸준한 다수의 수정활동을 통해서 'W-let'의 생명력을 유지함으로써 지식의 실제적인 변화를 반영한다. 생산된 'W-let'들은 위키형 집단지성 서비스의 데이터베이스에 축적되고, 이것들은 내부링크를 통해서 모두 연결되어 있다. 백과사전 형식으로 하나의 개념어를 설명하는 하나의 아티클은 오로지 사실적인 지식들로만 구성되나 내부링크와 외부링크를 통해서 다양한 스펙트럼을 가지는 모델로 설정하였다. 위와 같이 설정된 모델을 바탕으로 공통된 질의어 및 개념어를 선정하여 각각의 서비스에 노출시켰다. 이를 통해서 얻어진 각 서비스의 데이터베이스에 축적된 모든 데이터들 중에서 일정한 기간을 기준으로 각각의 모델 검증에 필요한 데이터를 추출하여 분석하는 방식으로 진행되었다. 그 결과 지식검색형 집단지성에서는 '질문-답변-채택'의 생산 구조 속에 다수가 참여하여 질문-채택답변-기타답변으로 배열되어 있는 완성된 형태의 K-let들을 지속적으로 생산하며 비슷한 성향을 가진 K-let들이 반복적으로 생산되어 지식검색 데이터베이스에 누적된다. 지식 소비자들은 질의어 검색을 통해서 다양한 K-let들을 선택하여 비교, 검토한 후에 선택된 K-let들의 배열은 해체되어 소비자들에 의해서 재배열됨을 발견할 수 있었다. 이에 지식검색형 집단지성이란 다수의 의해서 생산되고 누적된 지식들이 소비자의 검색과 선택에 의해 해체되어 재배열되는 지식의 맞춤화 과정이라고 정의내릴 수 있었다. 반면에 위키형 집단지성에서는 '내용입력-미세수정' 구조 속에서 생명력 있는 W-let을 생성한다. W-let은 백과사전처럼 정리되어 내부링크를 통해서 서로 연결되고, 외부링크를 통해 확장되고, 지식소비자들은 검색을 통해 최초의 W-let에 도달한 후에 링크를 선택함으로써 지식을 확장시킴을 검증할 수 있었다. 따라서 위키형 집단지성이란 다수의 의해서 생산되고 정리된 지식들이 소비자의 검색과 링크에 의해 무한히 확장되는 지식의 확대 재생산되는 과정이라고 정의 내릴 수 있다. 결국, 현재의 집단지성이란 지식이 다수의 참여로 생산됨으로써 개인에게 맞춤화되고, 끊임없이 확대 재생산되는 과정을 의미한다. 그리고 이러한 집단지성의 방식은 지식이라는 현재의 차원을 넘어서 정치, 경제를 비롯한 사회의 전 영역으로 점차적으로 확대되어갈 것이다. 앞으로 연구들은 두 가지 모델이 혼재되어 있는 현재의 집단지성이 어떠한 새로운 모델을 만들면서 다른 영역으로 확장되어갈 것인지에 대해서 초점을 맞춰 나가야할 것이다.

• Korean Journal of Cognitive Science
• /
• v.19 no.2
• /
• pp.177-203
• /
• 2008

The present study was aimed to compare the semantic systems represented by the lexicon between L1 and L2 in late Korean-English bilinguals. The participants performed the word-picture matching task. the task was to decide whether the pictures represent the previously presented words' meaning. The words were the basic level categories. The stimuli were consisted of common object belonged to two different semantic categories (natural and artificial). To control the translation strategies, the SOA were manipulated as 650ms(Exp. 1) and 250ms(Exp. 2). No translation effort was found in the comparison of the two experiments. In both experiment, the RTs were faster in L1 rendition, and it took longer to decide the stimuli in natural categories than with artificial ones in L1. However, this category effect was not observed in L2. The results showed the differences in the organization of semantic representations in the brain through the bilinguals' two languages. While L1 semantic knowledge might be more systematically organized, that of L2 seems to be less well organized, at least by late bilinguals who participated in the present study.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.111-118
• /
• 2015

Entity linking is to link entity's name mentions occurring in text to corresponding entities within knowledge bases. Since the same entity mention may refer to different entities according to their context, entity linking needs to deal with entity disambiguation. Most recent works on entity disambiguation focus on semantic relatedness between entities and attempt to integrate semantic relatedness with entity prior probabilities and term co-occurrence. To the best of my knowledge, however, it is hard to find studies that analyze and present the pure effects of semantic relatedness on entity disambiguation. From the experimentation on Korean Wikipedia data set, this article empirically evaluates entity disambiguation approaches using semantic relatedness in terms of the following aspects: (1) the difference among semantic relatedness measures such as NGD, PMI, Jaccard, Dice, Simpson, (2) the influence of ambiguities in co-occurring entity mentions' set, and (3) the difference between individual and collective disambiguation approaches.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.1-9
• /
• 2009

Many techniques have been proposed to store efficiently and query XML data. One way achieving this goal is using relational database by transforming XML data into relational format. But most researches only transformed content and structure of XML schema. Although they transformed semantic constrainment of XML schema, they did not all of semantics. In this paper, we propose a systematic technique for extracting semantic constrainment from XML schema and storing method when the extracting result is transformed into relational schema without any lost of semantic constrainment. The transforming algorithm is used for extracting and storing semantic constrainment from XML schema and it shows how extracted information is stored according to schema notation. Also it provides semantic knowledges that are needed to be confirmed during the transformation to ensure a correct relation schema. The technique can reduce storage redundancy and can keep up content and structure with integrity constraints.

• Korean Journal of Cognitive Science
• /
• v.27 no.1
• /
• pp.27-41
• /
• 2016

Named entity recognition is to classify elements in text into predefined categories and used for various departments which receives natural language inputs. In this paper, we propose a method which can generate named entity training corpus automatically using knowledge bases. We apply two different methods to generate corpus depending on the knowledge bases. One of the methods attaches named entity labels to text data using Wikipedia. The other method crawls data from web and labels named entities to web text data using Freebase. We conduct two experiments to evaluate corpus quality and our proposed method for generating Named entity recognition corpus automatically. We extract sentences randomly from two corpus which called Wikipedia corpus and Web corpus then label them to validate both automatic labeled corpus. We also show the performance of named entity recognizer trained by corpus generated in our proposed method. The result shows that our proposed method adapts well with new corpus which reflects diverse sentence structures and the newest entities.

• Journal of the Korean School Mathematics Society
• /
• v.24 no.1
• /
• pp.127-150
• /
• 2021

Recently, in the field of mathematics education, mathematical noticing has been considered as an important element of teacher expertise. The meaning of mathematical noticing is the ability of teachers to notice and interpret significant events among various events that occur in mathematics class. This study attempts to analyze the differences of pre-service secondary teachers' mathematical noticing and confirm the factors that cause the differences between them. To accomplish this, the items on class critiques were established to identify pre-service secondary school teachers' mathematical noticing, and each of 18 pre-service secondary mathematics teachers were required to write a class critique by watching a video in which their micro-teaching was recorded. It was that the teachers' mathematical noticing can be identified by analyzing their critiques in three dimensions such as actor, topic, and stance. As a result, there were differences in mathematical noticing between pre-service secondary mathematical teachers in terms of topic and stance dimensions. The result suggests that teachers' mathematicl noticing can be differentiated by subject matter knowledge, pedagogical content knowledge, curricular knowledge, beliefs, experiences, goals, and practical knowledge.

• (The)Study of the Eastern Classic
• /
• no.32
• /
• pp.159-187
• /
• 2008

This article aims to investigate the change of theories of reading and its historical meaning in the later Joseon period. Three scholar who left major theories of reading are mainly analyzed for the sake of it. Park, Se-chae(1631-1695) was a Neo-Confucianist who had the theory of reading named Dokseo-Gungliron(讀書窮理論). It was totally based on the scheme of Neo-Confucianist instruction and concentrated on mastering the moral principles with relishing the sentences of the Confucian Canons. Jeong, Yak-yong(1762-1836) was a Practical learning scholar and then criticized the moral-centric theory of reading of Neo-Confucianism. He valued much of the Confucian Canons but also focused on erudite reading so as to enlarge practical knowledge. Hong, Gil-ju(1786-1841) was a stylist and presented a severe criticism against Neo-Confucianist theory of reading as much. He thought that what we could realize with reading are the principles of the individual, not of the whole. The change of theories of reading in the later Joseon period as above reveals us the fact that the intellectual history of that period was in the process of dynamical change.