• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.1-11
• /
• 2002

In this paper, a test was performed to determine whether words in Anchor Text were appropriate as key words. As a result of the test. there were proper words of high weighting factor, while some others did not even appear in the text. therefore, were not appropriate as key words. In order to resolve this problem. a new method was proposed to extract key words. Using the proposed method, inappropriate key words can be removed so that new key words be set, and then, ranking becomes possible with the TFIDF value as a weighting factor of the key word. It was verified that the new method has higher accuracy compared to the previous methods.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.25-34
• /
• 2001

지식을 관리하는 것에 주력했던 기존의 인공지능 연구 방향은 동적으로 움직이는 외부 환경에서 적응할 수 있는 시스템 구축으로 변화하고 있다. 이러한 시스템의 기본 능력을 이루는 많은 학습방법 중에서 비교적 최근에 제시된 강화학습은 일반적인 사례에 적용하기 쉽고 동적인 환경에서 뛰어난 적응 능력을 보여주었다. 이런 장점을 바탕으로 강화학습은 에이전트 연구에 많이 사용되고 있다. 하지만, 현재까지 연구결과는 강화학습으로 구축된 에이전트로 해결할 수 있는 작업의 난이도에 한계가 있음을 보이고 있다. 특히, 복수의 부분 작업으로 구성되어 있는 작업을 처리할 경우에 기본의 강화학습 방법은 문제 해결에 한계를 보여주고 있다. 본 논문에서는 복수의 부분 작업으로 구성된 작업이 왜 처리하기 힘든가를 분석하고, 이런 문제를 처리할 수 있는 방안을 제안한다. 본 논문에서 제안하고 있는 EQ-Learning의 강화학습 방법의 대표적인 Q-Learning을 확장시켜 문제를 해결한다. 이 방법은 각각의 부분 작업 해결 방안을 학습시키고 그 학습 결과들의 적절한 순서를 찾아내 전체 작업을 해결한다. EQ-Learning의 타당성을 검증하기 위해 격자 공간에서 복수의 부분작업으로 구성된 미로 문제를 통하여 실험하였다.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.73-86
• /
• 1990

This study aims to give a syntactic and semantic analysis of the phe- nomenon of Quantifier Floating in the framework of Generalixed Cate- gorial Grammar. Floated quantifiers like neys-i as in Hakayngtul-i neys-i swul-ul masyessta are syntactically analyxed as VP modifiers(VP/VP), and semantically as involving nominalixed properties. Related forms like neys(NP/NP) and neys-ul(TV-TV) are also given rigorous syntactic and semantic analysis. A successful anaysis sheds light on the possiblity of using Categorial Grammar, which is subject to adjacency principle, for the (computer) processing od Korean.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.15-32
• /
• 1990

In the area of natural language processing, a lot of unification-based grammar formalisms have been issued and are highlighted. The core of the formalisms is an unification of feature stutures. But few formal unification methodologies have been developed. Therfore, implementers of the formalisms could not help adopting an ad hoc design strategy for the unification module. In this paper, we suggest an efficient unification methodology using FUL, a programming language whic supports the unification. For the exeample, we will trace the unification processes in LFG and HPSG, the representative unification-based grammar formalisms, with FUL.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.51-72
• /
• 1990

This study investigated the effects of macrostructure on discourse processing. In this study, three different story were employed to form macrostructures on different times, and reading time, sentence verification time and free recall rate were measured as dependent vari- ables. The results showed that forming the macrostructure influenced the reading and verification times and the recall rate. The results were interpreted to indicate that the macrostructure is important to comprehend and recall the stories, and that the story grammars, hierarchies of story schema and causal relation of sentences affect the comprehension and recall through their interaction in macrostructure.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.193-204
• /
• 1990

This paper discusses a reasoning model of information retrieval with a hierarchical thesaurus.The model computes the conceptual distance between a query and an object,both are indexed with weighted terms from a hierarchical thesaurus. The proposed model allows Boolean operators for user queries and edge weights for a hierarchical thesaurus. Experimental results have shown that the proposed model simulates, with surprising accuracy, people in the assessment of conceptual closeness between queries objects.

• Korean Journal of Cognitive Science
• /
• v.2 no.1
• /
• pp.167-192
• /
• 1990

It is undeniable that the meanings usedinpractice are agreed feelings in the limited universe of discourerse of among the cognators of the linguistic expressions.The fact that the feelings are relative can be shown indirectly in terms of the indeterminacy of translations,because the feelings are not the physical object which can be visible or audible.However the agreed feelins also are not the absolute meanings,therefore these agreemnts are also relative depending on the situations used.

• Korean Journal of Cognitive Science
• /
• v.14 no.4
• /
• pp.43-51
• /
• 2003

The present paper is concerned with assessing both communicational skills and grammatical knowledge in three Korean-speaking children with a range in age from 9;11 to 12;2 and in MLU from 1.68 to 2.22. It was found that all three autistic children's speech was largely repetitive and echolalic, unable to consistently interact communicatively on the ongoing joint focus of attention. It was also observed that the more repetitive the child speech was, the more impaired morpho-syntactically it was. Based on these findings, it was speculated that the deficit in joint focus of attention might relate to grammatical development.

• Korean Journal of Cognitive Science
• /
• v.10 no.1
• /
• pp.13-24
• /
• 1999

In this paper, we propose a classifier based on modular networks using an unsupervised learning method. The structure of each module is designed through stochastic analysis of input data and each module classifier data independently. The result of independent classification of each module and a measure of the nearest distance are integrated during the final data classification phase to allow more precise c classification. Computation time is decreased by deleting modules that have been classified to be incorrect during the final classification phase. Using this method. a neural network sharing the best performance was implemented without considering. lots of of variables which can affect the performance of the neural network.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2006.06a
• /
• pp.9-14
• /
• 2006

본고는 한국어 교육방식의 하나라고 할 수 있는 한국어 어휘를 대상으로 한문제 출제 방식에서 문제 은행식 출제 방식이 갖고 있는 여러 가지 문제점을 해소할 수 있는 하나의 방법으로서 한국어 어휘 학습 시스템을 위한 자동문제 생성 기술을 제시한다. 먼저 기존 한국어 어휘 문제의 문항 분석 결과를 바탕으로 8가지 어휘력 평가 유형 및 각 유형별 자동 문제 생성 패턴을 구축하고, 한국어 어휘에 대한 풍부한 정보를 담고 있는 국어사전을 기반으로 한 자동 한국어 어휘 문제 생성 기술을 제시한다.