• Korean Journal of Cognitive Science
• /
• v.28 no.2
• /
• pp.111-131
• /
• 2017

The connectionist model is one approach to studying language processing from a computational perspective. And building a representation in the connectionist model study is just as important as making the structure of the model in that it determines the level of learning and performance of the model. The connectionist model has been constructed in two different ways: localist representation and distributed representation. However, the localist representation used in the previous studies had limitations in that the unit of the output layer having a rare target activation value is inactivated, and the past distributed representation has the limitation of difficulty in confirming the result by the opacity of the displayed information. This has been a limitation of the overall connection model study. In this paper, we present a new method to induce distributed representation with local representation using abstraction of information, which is a feature of restricted Boltzmann machine, with respect to the limitation of such representation of the past. As a result, our proposed method effectively solves the problem of conventional representation by using the method of information compression and inverse transformation of distributed representation into local representation.

• School Mathematics
• /
• v.12 no.4
• /
• pp.605-617
• /
• 2010

This study explores the characteristics and roles of non-textual elements in secondary mathematics textbooks in the United States and South Korea, using a conceptual framework that I have developed: variety, contextuality, and connectivity. Analyzing five U.S. standards-based textbooks and 13 Korean textbooks, this study shows that although non-textual elements in mathematics textbooks are free of literal language, they exhibit different emphases and reflect assumptions about what is important in learning mathematics and how it can be taught and learned in a particular societal context (Mishra, 1999; Zazkis & Gadowsky, 2001). While there are similar patterns in the use of different types of non-textual elements in textbooks from both countries, different opportunities are provided for students to learn mathematics between the two countries.

• Journal of the Korean Chemical Society
• /
• v.64 no.6
• /
• pp.416-428
• /
• 2020

This study analyzed the uses of external representations presented in the matter units of the 7th-grade science digital textbooks developed under the 2015 revised national curriculum. The level, form, presentation, and interactivity of external representations presented in 5 types of digital textbooks were analyzed. As for the level, the macroscopic level of representations was mainly presented. The macroscopic level and microscopic level of representations were presented together in the particle description. As for the form, visual-verbal and visual-nonverbal representations were usually presented across the board. Very few audial-verbal and audial-nonverbal representations were presented. Visual-verbal and audial-verbal representations were mostly presented in formal form, and visual-nonverbal representations were mostly presented in illustration without movement. The presentation of representations was analyzed in three aspects. First, visual-verbal and visual-nonverbal representations were mainly presented together and none of audial-verbal and visual-nonverbal representations were presented together. When the representations of the audial-verbal, visual-nonverbal, and visual-verbal were presented together, some of the information presented in audial-verbal representations was repeatedly presented in the visual-verbal representations. Second, audial-nonverbal representations not related to learning content were presented along with other representations. Third, there were few cases of arranging visual-verbal and visual-nonverbal representations on the next pages. Audialverbal and visual-nonverbal representations were always presented synchronized. As for the interactivity, the manipulation level was mainly presented in the main area, and the feedback level was mainly presented in the activity area. The adaptation level and the communication level of interactivity were presented very few. Based on the results, the implications for the direction of constructing digital textbooks were discussed.

• 한국지구과학회:학술대회논문집
• /
• 2006.02a
• /
• pp.92-92
• /
• 2006

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.817-826
• /
• 2002

In Korean dialogue honorification phenomenon may occur, an honorific pronoun may be used, and a subject or an object may be completely omitted when it can be recovered based on context. This paper proposes that in order to process Korean dialogue in which such distinct linguistic phenomena occur and to construct its representation structure we mark and use the following information explicitly, not implicitly : information about dialogue participants, information about the speech act of an utterance, information about the relative order of social status for the people involved in dialogue, and information flow among utterances of dialogue. In addition, this paper presents a method of marking and using such situational information and an appropriate representation structure of Korean dialogue. In this paper we set up Korean dialogue representation structure by modifying and extending DRT (Discourse Representation Theory) and SDRT (Segmented Discourse Representation Theory). Futhermore, this paper shows how to process Korean dialogue computationally and construct its representation structure by using Prolog programming language, and then applies such representation structure to spontaneous Korean dialogue to know its validity.

• Korean Journal of Cognitive Science
• /
• v.19 no.1
• /
• pp.75-88
• /
• 2008

Visual scene contains lots of redundant information. To process this redundant information without increasing brain's volume, human visual system may summarize incoming information. If similar but different information are given to visual system, visual system extracts statistical properties of the information. One example of the statistical representation is representation of mean size. The mean representation is accurate and durable. The process of mean representation is suggested to be parallel. However, previous studies on the mean representation mostly used behavioral methods. The purpose of this study was to investigate which neural regions extracted the mean size of a set of circles using fMRI method. According to previous studies, BOLD signal of certain areas that were in charge of cousin stimuli decreased when the same stimuli presented repetitively. We used this paradigm and found that BOLD signal of right occipital area was decreased when same mean site was presented repeatedly. This results suggest that right occipital area is the locus of mean representation of visual stimuli.

• Journal of The Korean Association For Science Education
• /
• v.27 no.3
• /
• pp.190-200
• /
• 2007

In this study, we analyzed the uses of external representations in material units of 7th grade science textbooks developed under the 7th National Curriculum on the basis of theories and research results on learning with multiple representations. The results revealed that the frequencies of microscopic external representations were higher than those of macroscopic and symbolic external representations. The external representations with drawing and/or writing were presented more frequently than those without drawing and/or writing. Furthermore, the external representations were rarely presented on the basis of the principles (e.g., personalization principle) and/or theories (e.g., dual coding theory, cognitive load theory, and social constructivism theory) for effective uses of the external representations in learning with multiple representations. Educational implications are discussed.

• Journal of architectural history
• /
• v.15 no.2
• /
• pp.163-170
• /
• 2006

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.3-7
• /
• 2019

자연어 표상은 자연어가 가진 정보를 컴퓨터에게 전달하기 위해 표현하는 방법이다. 현재 자연어 표상은 학습을 통해 고정된 벡터로 표현하는 것이 아닌 문맥적 정보에 의해 벡터가 변화한다. 그 중 BERT의 경우 Transformer 모델의 encoder를 사용하여 자연어를 표상하는 기술이다. 하지만 BERT의 경우 학습시간이 많이 걸리며, 대용량의 데이터를 필요로 한다. 본 논문에서는 빠른 자연어 표상 학습을 위해 의미 정보와 BERT를 결합한 개념 언어 모델을 제안한다. 의미 정보로 단어의 품사 정보와, 명사의 의미 계층 정보를 추상적으로 표현했다. 실험을 위해 ETRI에서 공개한 한국어 BERT 모델을 비교 대상으로 하며, 개체명 인식을 학습하여 비교했다. 두 모델의 개체명 인식 결과가 비슷하게 나타났다. 의미 정보가 자연어 표상을 하는데 중요한 정보가 될 수 있음을 확인했다.

• Journal of The Korean Association For Science Education
• /
• v.37 no.2
• /
• pp.253-262
• /
• 2017

This study aims at investigating the perceptions of science teachers about the role of visual representations in the teaching of electromagnetism, and finding out how science teachers use visual representations in their teaching of electromagnetism and the difficulties they experience in dealing with those representations. A total of 121 science teachers responded to the online survey. The results showed that most of the teachers agreed to the significance of using visual representations in the classroom but regarded their role as means of simply delivering science knowledge rather than constructing or generating knowledge. For the three visual representations widely used in teaching of electromagnetism in secondary schools (electrostatic induction on electroscope, magnetic field around current carrying wire, structure and principle of electric motor), the teachers preferred teacher-centered use of visual representations rather than student-centered and teacher's construction of representations were the most frequent among four types of use; interpretation, construction, application, and evaluation. The difficulties of teaching with these three visual representations were categorized into several factors; teachers, students, the characteristics of the representations, and lack of resources and classroom environment. Teachers' limited perceptions about the role of visual representations were associated with the ways of using visual representations in their teaching. Implications for the effective use of visual representations for science learning and teaching were discussed.