• The KIPS Transactions:PartA
• /
• v.15A no.2
• /
• pp.125-134
• /
• 2008

We implemented a system being able to suggest example sentences for multiple choice tests, considering the level of students. To build the system, we designed an automatic method for sentence generation, which made it possible to control the difficulty degree of questions. For the proper evaluation in the multiple choice tests, proper size of question pools is required. To satisfy this requirement, a system which can generate various and numerous questions and their example sentences in a fast way should be used. In this paper, we designed an automatic generation method using a linguistic resource called WordNet. For the automatic generation, firstly, we extracted keywords from the existing sentences with the morphological analysis and candidate terms with similar meaning to the keywords in Korean WordNet space are suggested. When suggesting candidate terms, we transformed the existing Korean WordNet scheme into a new scheme to construct the concept similarity matrix. The similarity degree between concepts can be ranged from 0, representing synonyms relationships, to 9, representing non-connected relationships. By using the degree, we can control the difficulty degree of newly generated questions. We used two methods for evaluating semantic similarity between two concepts. The first one is considering only the distance between two concepts and the second one additionally considers positions of two concepts in the Korean Wordnet space. With these methods, we can build a system which can help the instructors generate new questions and their example sentences with various contents and difficulty degree from existing sentences more easily.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.225-248
• /
• 1992

In this paper, word sense disambiguation methods utilizing a knowledge base based on a semantic network are introduced. The basic idea is to keep track of a set of paths in the knowledge base which correspond to the inctemental semantic interpretation of a input sentence. These paths are called the semantic paths. when the parser reads a word, the senses of this word which are not involved in any of the semantic paths are removed. Then the removal operation is propagated through the knowledge base to invoke the removal of the senses of other words that have been read before. This removal operation is called recusively as long as senses can be removed. This is called the recursive word sense removal. Concretion of a vague word's concept is one of the important word sense disambiguation methods. We introduce a method called the path adjustment that extends the conctetion operation. How to use semantic association or syntactic processing in coorporation with the above methods is also considered.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7718-7728
• /
• 2015

Semantic similarity between words can be applied in many fields including computational linguistics, artificial intelligence, and information retrieval. In this paper, we present weighted method for measuring a semantic similarity between words in a document. This method uses edge distance and depth of WordNet. The method calculates a semantic similarity between words on the basis of document information. Document information uses word term frequencies(TF) and word concept frequencies(CF). Each word weight value is calculated by TF and CF in the document. The method includes the edge distance between words, the depth of subsumer, and the word weight in the document. We compared out scheme with the other method by experiments. As the result, the proposed method outperforms other similarity measures. In the document, the word weight value is calculated by the proposed method. Other methods which based simple shortest distance or depth had difficult to represent the information or merge informations. This paper considered shortest distance, depth and information of words in the document, and also improved the performance.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.4
• /
• pp.299-303
• /
• 2009

Patent information search is used for checking existence of earlier works. In patent information search, there are many reasons that fails to get appropriate information. This research proposes a method extracting alternative word candidates in order to minimize search failure due to keyword mismatch. Assuming that two words have similar meaning if they have similar co-occurrence words, the proposed method uses the concept of concentration, association word set, cosine similarity between association word sets and a ranking modification technique. Performance of the proposed method is evaluated using a manually extracted alternative word candidate list. Evaluation results show that the proposed method outperforms the document vector space model in recall.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.90-97
• /
• 2003

This paper proposes a speech recognition based on HMM(Hidden Markov Model) using FSVQ(First Section Vector Quantization) and fuzzy concept. In the proposed paper, we generate codebook of First Section, and then obtain multi-observation sequences by order of large propabilistic values based on fuzzy rule from the codebook of the first section. Thereafter, this observation sequences of first section from codebooks is trained and in case of recognition, a word that has the most highest probability of first section is selected as a recognized word by same concept. Train station names are selected as the target recognition vocabulary and LPC cepstrum coefficients are used as the feature parameters. Besides the speech recognition experiments of proposed method, we experiment the other methods under same conditions and data. Through the experiment results, it is proved that the proposed method based on HMM using FSVQ and fuzzy concept is superior to tile others in recognition rate.

• 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.16 no.1
• /
• pp.77-86
• /
• 1996

The purpose of this study was to review the studies related to concept learning forcusing on the meanings, kinds, and characteristics of concepts. Then the characteristics of the concepts were analyzed in the three positions: metaphysics, epistemology, and psychology. It was identified that the word 'concept' were confused with the other words such as conception, construct, idea, notion, identity. It was also found that researchers defined the concepts by the use of various meanings. The instructional strategies for scientific concepts were also analyzed in this study. The study found that the instructional strategies for concept learning were developed according to the views about the nature of concepts. Described on the paper are three types of instructional models for science concepts suggested by constructivists as follows: concept formation, concept differentiation, and exchange. They developed the models based on the current research on the misconceptions of major scientific concepts.

• Korean System Dynamics Review
• /
• v.14 no.2
• /
• pp.5-30
• /
• 2013

The concept of resilience in complex and adaptive socio-economic systems, has been a buzz word in international societies and academies related to policy makers for sustainable development since some years ago. This paper deals with an application of the resilient concept, which has been told since the last some decades in the field of ecology and applied system sciences, to social science especially in system dynamics. First the author introduces the concept of equilibrium stability and resilience in simple dynamic models, and moreover provides the behavioral characteristics and examples of system resilience in terms of system dynamics. The concept of resilience in structural perspectives are also discussed with the topics of panarchy and adaptive renewal cycles, etc.

• School Mathematics
• /
• v.4 no.2
• /
• pp.247-260
• /
• 2002

In recent elementary school mathematics a word 'stipulation' newly appears. The word is used instead of definition. However, there seems to be some differences between definition and stipulation. So, in this paper we investigate those differences through the concept 'function of definition'. In school mathematics textbooks there are definitions which carry out special functions In mathematical contexts or situations. We can say that we understand those definitions, only if we also understand the functions of definitions in those contexts or situations. Functions of definition are classified as, stipulation-function, discrimination-function, analysis-function, demonstration-function, improvement-function. With these analyses we made a frame for investigating the characteristics of the definitions in recent elementary school mathematics textbooks. As a result of analysing functions of definition we found that generally speaking, stipulation-function is excessively emphasized and the other functions of definition are not explained adequately in school mathematics textbooks. So it is required that the textbook authors should be careful not to miss an opportunity for the functional understanding and the mathematics teachers should be aware of the functions of definitions. Finally, we comment that textbook author, teacher, and researcher should be careful in using the word 'stipulation' instead of definition, because, although there are various functions of definitions, students might ream only stipulation-function.

• School Mathematics
• /
• v.11 no.3
• /
• pp.479-496
• /
• 2009

Some children can construct a basic concept of addition and subtraction during the preschool years. Children start to experience mathematics via numbers and their of operations and contact with various contexts of addition and subtraction. In special, word problems reflect mathematics which is appliable to real life. In this paper, I analyse the types of word problems in text book and its students' responses. First, I analyse the types of addition word problems which consist of change add-into situations and part-part-whole situations. Second, I analyse the types of subtraction word problems which consist of change take-away situations, compare situations and equalize situations. Third, I analyse the students' responses by the types of word problems in addition and subtraction. And 115 2nd grade elementary school students participated in this survey. The following results have been drawn from this study. First, the proposition of word problems of part-part-whole situations is higher than that of change add-into situations and the proposition of word problems of take-away situations is higher than that of compare situations and equalize situations. According to the analysis about students' responses, It is no difference between change add-into situations and part-part-whole situations. But the proposition of word problems of take-away situations is higher than that of compare situations and equalize situations. This results from word problems which contain unnecessary information in problem. So, we have to present the various word problems to students.