• 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 the Korea Academia-Industrial cooperation Society
• /
• v.5 no.6
• /
• pp.539-545
• /
• 2004

For question answering system that extracts an answer and output to user‘s natural language question, a process of question type classification from user’s natural language query is very important. This paper proposes a question and answer type classifier using the interrogatives and word semantic categories instead of complicated classifying rules and huge dictionaries. Synonyms and postfix information are also used for question type classification. Experiments show that the semantic categories are helpful for question type classifying without interrogatives.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.466-475
• /
• 2003

To build an efficient Question-Answering (QA) system, a question type classifier is needed. It can classify user's queries into predefined categories regardless of the surface form of a question. In this paper, we propose a question type classifier using a Support Vector Machine (SVM). The question type classifier first extracts features like lexical forms, part of speech and semantic markers from a user's question. The system uses $X^2$ statistic to select important features. Selected features are represented as a vector. Finally, a SVM categorizes questions into predefined categories according to the extracted features. In the experiment, the proposed system accomplished 86.4% accuracy The system precisely classifies question type without using any rules like lexico-syntactic patterns. Therefore, the system is robust and easily portable to other domains.

• Journal of Sasang Constitutional Medicine
• /
• v.15 no.3
• /
• pp.124-138
• /
• 2003

Objectives : To evaluate the properness and effectiveness of the question categories concerning 'sasang constitutional characteristics of mind', used in Iksan Wonkwang Oriental Medicine. Methods : We statistically analyzed data from those 1335 patients focussing on 'relative discrimination ability' to sasang constructions and 'response ratio'. Patients included in this research are only those who had been well treated in Iksan Wonkwang Oriental Medicine during the Period of three years from 2000 to 2002. The data are obtained through the electronic chart developed by Kim Jong-Yeal, and analyzed using the statistical Package SPSS. Results: In total characteristics of mind, the question category of 'timid' has high discriminating power and effectiveness to Soeum type, more in women than men, and especially with an age of 21 or more; The category of 'hasty-tempered' to Soyang type in women with all ages and men with ages 21-40; The category of 'broad-minded' to Taeum type with ages 41 or more; The category of 'timid and broad-minded' to Soyang type, and especially high to women with ages 41 or more. Question categories concerning response type in anger were estimated to have different response patterns to sasang constructions only for ages 21 or more by $X^2$2 test. The question category of 'bear and last long' has high discriminating power and effectiveness to Soeum type, more in men than women, and increasingly to ages; The category of 'impatient and disarmed quickly' to Soyang type in both women and men, especially with ages 21 or more; The category of 'impatient' to Soyang type women or with ages 21 or more. Other categories have low discriminating power or low effectiveness. Concernig expression type of one's thought, the question category of 'straightly' has high discriminating power and effectiveness to Soyang type, more in wemen than men, and especially to ages 21 or more; The category of 'tender' to Soeum type, in women or with ages 40 or less; The category of 'indirectly' to Taeum type in men or with ages 41 or more; The category of 'straightly and stuborn' to Soyang type with ages 41 or more; The category of 'indirectly and tender' to Soeum with with ages 20 or less; The category of 'not express and tender' to Soeum type with ages 41 or more; Conclusions : Question categories concerning total characteristics of mind, response type in anger and expression type of one's thought, are partially discriminating and effective to specific constitution according to sex and ages, and some categories are more discriminating and effective when they are composited. But generally, the discriminating power of Taeum constitution group and group with ages 20 or less was too low, so it is necessary to develope question categories for those groups.

• Journal of the Korean Society for information Management
• /
• v.21 no.4 s.54
• /
• pp.251-263
• /
• 2004

For question-answering system, question analysis module finds the question points from user's natural language questions, classifies the question types, and extracts some useful information for answer. This paper proposes a question type classifying technique based on focus words extracted from questions and word semantic information, instead of complicated rules or huge knowledge resources. It also shows how to find the question type without focus words, and how useful the synonym or postfix information to enhance the performance of classifying module.

• Journal of Science Education
• /
• v.39 no.1
• /
• pp.58-79
• /
• 2015

This study is to analyze the 2289 students questionnaires from 3rd to 9th grade students in order to analyze the students' perceptions change aspect by their grade about the frequency and type of students' question during various science class context. After the class contexts proposed in the questionnaire subcategorize into 19 subitems about 4 areas of class content, class pattern, class material and class process, this study examined the frequency and type of students' question during a science class by each item. The results of this study were as follows. First, the type of students' question was that the most frequent was understanding question and the second was memory question and these both types were half frequency. There was no special tendency related the change of students' question type by school year. Second, the frequency of 4th grade students' question was the highest among other school year students and the frequency of students' question was lowered by the higher school year. The change of students' question by school year was the biggest between 3rd and 4th grade. The class strategies for improving the class effect reflect that the various and active students' question by class context and school year stimulates students' thinking and also builds up the active class environment.

• Journal of Korean Elementary Science Education
• /
• v.36 no.4
• /
• pp.331-345
• /
• 2017

The purpose of this study is to collect and analyze the student's pre-inquire and to obtain information on how to use the teaching-learning process. The specific research problem is to confirm the level of the student's pre-inquire, to identify the characteristics of each type, and to check what pre-inquire can be used in the teaching-learning process. The research was conducted on 149 children in the $3^{rd}$ and $4^{th}$ grade of elementary school, and collected a total of 2,034 inquires. As a result of analyzing three times, the students' pre-inquires accounted for 90% of Level 2 and Level 3, which are the inquires that give meaningful answers in the teaching-learning process. These results show that the pre-inquires presented before the students take up the new lesson are not low-level inquires and they can present meaningful inquires that can be used for teaching-learning. Next, as a result of analyzing the student's inquire by type, the factual question was the largest with 50%, followed by comprehension question, procedural question, application question, and prediction question. The factual and procedural questions showed that they could be used as learning activities during the teaching-learning process. Comprehension questions included in the wonderment question can be used as a learning question. And the application question is a question that can be applied to deepening activities, and the prediction question can be used in the inquiry and experiment process of learning activities.

• ETRI Journal
• /
• v.39 no.2
• /
• pp.191-201
• /
• 2017

This paper proposes an approach using taxonomic relatedness for answer-type recognition and type coercion in a question-answering system. We introduce a question analysis method for a lexical answer type (LAT) and semantic answer type (SAT) and describe the construction of a taxonomy linking them. We also analyze the effectiveness of type coercion based on the taxonomic relatedness of both ATs. Compared with the rule-based approach of IBM's Watson, our LAT detector, which combines rule-based and machine-learning approaches, achieves an 11.04% recall improvement without a sharp decline in precision. Our SAT classifier with a relatedness-based validation method achieves a precision of 73.55%. For type coercion using the taxonomic relatedness between both ATs and answer candidates, we construct an answer-type taxonomy that has a semantic relationship between the two ATs. In this paper, we introduce how to link heterogeneous lexical knowledge bases. We propose three strategies for type coercion based on the relatedness between the two ATs and answer candidates in this taxonomy. Finally, we demonstrate that this combination of individual type coercion creates a synergistic effect.

• Journal of the Korean Society of Earth Science Education
• /
• v.7 no.1
• /
• pp.64-74
• /
• 2014

The purpose of this study was to analyze the types of questions of energy field in the elementary science textbooks and to know the preference types of questions of students by grade. To accomplish this study, the analyzing framework on the types of questions was made and ensured the validity. To know students' preference types of questions, a questionnaire was made and the survey was conducted to the students of D elementary school in B city. The results can be summarized as follows: First, of the questions in the elementary science textbooks, the types of limited question were the most frequent(56%) and the next was the type of relevant question(41.82%). In the type of limited question, the element of propositional type was the most frequent and in the type of relevant question, the element of applicable type was the most frequent. Second, from the result of analyzing students' preference types of questions by grade using questionnaire, we could find as follows. Most of the graders chose retrospective type of question as the easy types of questions. And 3, 4, 6th graders chose justificative type and 5th graders chose applicable type as the difficult ones. Third, as interesting type and want-to-select type, 3th graders students chose propositional type and 4, 5th graders chose retrospective type and 6th graders chose inferring type.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.4
• /
• pp.149-154
• /
• 2014

A user should pick up relevant answers by himself from various search results when using user participation question answering community like Knowledge-iN. If refined answers are automatically provided, usability of question answering community must be improved. This paper divides questions in Q&A documents into 4 types(word, list, graph and text), then proposes summarizing methods for each question type using document statistics. Summarized answers for word, list and text type are obtained by question clustering and calculating scores for words using frequency, proximity and confidence of answers. Answers for graph type is shown by extracting user opinion from answers.