• The Journal of the Korea Contents Association
• /
• v.6 no.3
• /
• pp.12-19
• /
• 2006

In this paper, we describe a deep analysis of question for question answering system. It is difficult to offer the correct answer because general question answering systems do not analyze the semantic of user's natural language question. We analyze user's question semantically and extract semantic features using the semantic feature extraction grammar and characteristics of natural language question. They are represented as semantic features and grammatical morphemes that consider semantic and syntactic structure of user's questions. We evaluated our approach using 100 questions whose answer type is a person in the web. We showed that a deep analysis of questions which are comparatively short but enough to mean can analysis the user's intention and extract semantic features.

• Journal of Korean Elementary Science Education
• /
• v.26 no.5
• /
• pp.551-557
• /
• 2007

The purpose of this study was to examine the questions in the 'Matter' units of elementary science textbooks under the 7th curriculum. For the analysis, a total of 338 questions were extracted from 15 units. Six criteria (recalling, recognizing, predictive, applied, divergent, and evaluative question) were reconstructed for textbook question analysis based on Blosser(1973)'s question category system for science. The results were as follows. First, there were more closed (recalling, recognizing, predictive, or applied) questions (72.2%) than open (divergent or evaluative) questions (27.8%) in elementary science textbooks. Second, cognitive-memory (recalling or recognizing) question type was the most frequently asked in all grade levels. Open (divergent or evaluative) questions increased according to grade level whereas convergent (predictive or applied) questions decreased. Third, question types were applied based on the characteristics of each unit rather than on children's developmental characteristics. Educational implications were discussed based on the results.

• Journal of Korean Elementary Science Education
• /
• v.35 no.1
• /
• pp.1-12
• /
• 2016

The purpose of this study was to analyze question's patterns in elementary school science teacher's guide books of 5, 6th grade under the 2009 revised curriculum. A modified analysis framework based on Blosser's classified system was used to analyze 1,982 questions extracted from elementary science teacher's guide books by grade, by domain, and by teaching and learning stage. The findings of this study were as follows. First, of the 1,982 questions, the most prominent type of question was the propositional question and the following was the reproductive question. And, in comparing the question's patterns between 5, 6th grade, it was found that 6th grade had higher rate of close typed question, while 5th grade had higher rate of open typed question in its curriculum. Secondly, a comparative study about two domains, material and energy science domain and earth and life science domain, showed that the number of questions of each domain was not much different. However, it was found that propositional questions and applicable questions showed a higher rate in material and energy science domain, and anticipated questions and open typed questions including divergent and evaluative question showed higher rate in earth and life science domain. Moreover, although the total number of questions from integration and my fun research domain's contents was small, the rate of open typed questions was higher than any other domains. Finally, as a result of comparing and analyzing question's pattern in teaching and learning stages, the rate of reproductive question and anticipated questions was high at the stage of introduction. At the stage of development, the rate of propositional and reproductive questions was high. At the stage of conclusion, the rate of synthetic and applicable questions was high.

• Journal of Environmental Science International
• /
• v.6 no.3
• /
• pp.213-218
• /
• 1997

The question style In high school enoronmental science textbook was examined in terms of the placement, frequency, and type of question, and then analyzed the kind of scientific Inquiry process elicited by the question In the topic of textbook using the Tektbook guestioning Strategy Assessment Instrument (TQSAI). The average number of question per topic was only 0.6. The number of all Question In the high school enororunental science textbook was very little : the number of non-experiential Question was 8 and that of experiential one was 3. The total number of sentence was 1,236 and the ratio of the number of Question to that of sentence was 0.9% . The frequency of non-experlential question was higher than that of experiential one. In action part of the textbook, there were more kinds of Question styles than In the matin part.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.476-482
• /
• 2004

Question-Answering (QA) system has to analyze user's intention correctly to respond correct answer for user's question., This paper proposes a focus-word-based question analysis approach for Korean QA system to analyze user's intention correctly. focus-word is a clue-word which selects question type. The question type is determined to one in 75 subcategories using semantics of focus-words. the proposed system accomplished 97.18% accuracy for the main category and 95.31% accuracy for the subcategory in the question classification.

• International Journal of Contents
• /
• v.2 no.1
• /
• pp.17-21
• /
• 2006

In this paper, we describe a concept-based question-answering system in which concept rather than keyword itself makes an important role on both question analysis and answer extraction. Our idea is that concepts occurred in same type of questions are similar, and if a question is analyzed according to those concepts then we can extract more accurate answer because we know the semantic role of each word or phrase in question. Concept frame is defined for each type of question, and it is composed of important concepts in that question type. Currently the number of question type is 79 including 34 types for person, 14 types for location, and so on. We experiment this concept-based approach about questions which require person s name as their answer. Experimental results show that our system has high accuracy in answer extraction. Also, this concept-based approach can be used in combination with conventional approaches.

• Journal of Fisheries and Marine Sciences Education
• /
• v.26 no.4
• /
• pp.902-914
• /
• 2014

The purpose of this study is to provide useful information by analysis on mathematic classes for improve interactions between teacher and student using the Flanders Category System. For this, mathematic classes were observed by videotapes and recorded, 10 recorded videotapes were selected for analysis the property of linguistic interaction. The collected videotapes and records materials were transcribed by Advanced Flanders(AF) analysis program version 3.54. The detail investigated topics for studying are as follows. 1) What is the property of the Flanders 10 code analysis results? 2) What is the property of main and subsidiary linguistic flow of interaction? 3) What is the property of the Flanders index analysis results? The results of this study are as follow: 1) In Flanders 10 code analysis results, teacher's non-directive speaking is 12.76%, teacher's Indicative speaking is 50.28%, student's reactive speaking is 4.07%, student's voluntary speaking is 9.66%. 2) Among the 10 classes, 5 classes' main flow is 'ask convergent question ${\rightarrow}$ student's reactive speaking ${\rightarrow}$ lecture ${\rightarrow}$ ask convergent question', 2 classes' main flow is 'lecture ${\rightarrow}$ ask convergent question ${\rightarrow}$ student's reactive speaking ${\rightarrow}$ lecture', 3 classes' main and subsidiary flow is 'lecture ${\rightarrow}$ ask convergent question ${\rightarrow}$ lecture ${\rightarrow}$ work'. 3) In indices results, revised I/d ratio, student's speaking ratio, student question, wide answer ratio are higher than analysis standard and indirect ratio, teacher's question ratio are lower than analysis standard.

• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.144-147
• /
• 2015

Question Answering (QA) services can provide exact answers to user questions written in natural language form. This research focuses on how to build a QA system for a specific domain area. Online and offline QA system architecture of targeted domain such as domain detection, question analysis, reasoning, information retrieval, filtering, answer extraction, re-ranking, and answer generation, as well as data preparation are presented herein. Test results with an official Frequently Asked Question (FAQ) set showed 68% accuracy of the top 1 and 77% accuracy of the top 5. The contribution of each part such as question analysis system, document search engine, knowledge graph engine and re-ranking module for achieving the final answer are also presented.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.10-20
• /
• 2007

This paper describes a concept-based question analysis to analyze concept which is more important than keyword for the accurate answer extraction. Our idea is that we can extract correct answers from various paragraphs with different structures when we use well-defined concepts because concepts occurred in questions of same answer type are similar. That is, we will analyze the syntactic and semantic role of each word or phrase in a question in order to extract more relevant documents and more accurate answer in them. For each answer type, we define a concept frame which is composed of concepts commonly occurred in that type of questions and analyze user's question by filling a concept frame with a word or phrase. Empirical results show that our concept-based question analysis can extract more accurate answer than any other conventional approach. Also, concept-based approach has additional merits that it is language universal model, and can be combined with arbitrary conventional approaches.