• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of The Korean Association of Information Education
• /
• v.8 no.2
• /
• pp.251-259
• /
• 2004

Widespread internet service has brought many changes to modern life. Internet installed at school and intra-school computer network presented various education activities such as web-based instruction, immediate evaluation, and management of progress in studying. In this paper an essay question evaluation system for web service is studied for rapid measurement of accomplishment of student. This system provides evaluation of answers consisting a simple sentence and not demanding one word. If an essay question has exactly specified answer sheets and scoring criterion, this system give highly accurate scoring results, which shows nearly the same scoring of a teacher, needs very short time for evaluation, and represents real-time feed back result, so it is expected very high efficiency for the evaluation of an essay question.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.95-99
• /
• 2010

Social media refers to the content, which are created by users, such as blogs, social networks, and wikis. Recently, question-answering (QA) communities, in which users share information by questions and answers, are regarded as a kind of social media. Thus, QA communities have become a huge source of information for the past decade. However, it is hard for users to search the exact question-answer that is exactly matched with their needs as the number of question-answers increases in QA communities. This paper proposes an approach for classifying a question into three categories (information, opinion, and suggestion) according to the purpose of the question for more accurate information retrieval. Specifically, our approach is based on modified Na$\ddot{i}$ve Bayes classifier which uses structural characteristics of QA documents to improve the classification accuracy. Through our experiments, we achieved about 71.2% in classification accuracy.

• Journal of The Korean Association of Information Education
• /
• v.9 no.4
• /
• pp.673-684
• /
• 2005

In this research, we have developed a "computer tutor" that mimics the human tutor with animated tutoring dialog agent and the agent was integrated to teaching-learning material for elementary science subject. The developed system is a natural language based teaching-learning system using one-to-one dialogue. The developed pedagogical dialogue teaching-learning system analysis student's answer then provides appropriate answer or questions after comparing the student's answer with elementary school level achievement. When the agent gives either question or answer it uses the TTS(Text-to-Speech) function. Also the agent has an animated human tutor face for providing more human like feedback. The developed dialogue interface has been applied to 64 6th grade students. The test results show that the test group's average score is higher than the control group by 10.797. This shows that unlike conventional web courseware, our approach that "ask-answer" process and the animated character, which has human tutor's emotional expression, attracts students and helps to immerse to the courseware.

• Language and Information
• /
• v.14 no.2
• /
• pp.1-16
• /
• 2010

On the Inherent (non-) Negativity of Negative Sensitive Items. This paper explores the idea that Korean Negative Sensitive Items, which are better viewed as Negative Concord Items (NCIs) (Kim 2001, 2006, Watanabe 2004), should not be construed as inherently negative in spite of the fact that NCIs are able to appear as an elided form without the presence of a negative licenser. Among several diagnostics, which are designed to draw syntactic and semantic distinctions between traditional Negative Polarity Items (NPIs) and NCIs employed in previous studies, the ability of an NCI to appear as a fragment answer raises the question of whether the negativity of NCIs is inherent or not. Contrary to Kim (2001, 2006) and Watanabe (2004), who are in favor of the inherent negativity of NCIs, I claim that non-negative Korean NCIs still need contentful negation to be licensed, and therefore their ability to appear as a fragment answer should be considered as a matter of ellipsis, in support of Giannakidou (2000, 2006). The main argument will be strengthened by the fact that Korean NCIs do not express negative meaning themselves, and that double negation readings are not allowed no matter how many NCIs occur simultaneously.

• Journal of Korean Academy of Nursing
• /
• v.29 no.4
• /
• pp.841-854
• /
• 1999

This study tried to the answer to the question : “How does the human communication happen between clinical nurse and patient\ulcorner” To answer that, a micro-ethnographic research method was used and I performed field work at the orthopedic ward in one Korean metropolitan city. After analysis of interview data, observational data and field notes, I could understand that clinical nurse-patient communication performed for clinical decision making, providing patient education and emotional support. Prepared nurse communicate with patient more effectively, eventually can establish more trust relationship with patient. Conclusively I discussed about the way of nurse's skill acquisition, need of collaborative conference with doctor and nurse, and curriculum development to promote nurses's understanding of human.

• The Mathematical Education
• /
• v.52 no.1
• /
• pp.19-41
• /
• 2013

What is the foundation of mathematical thinking? Is it logic based symbolic language system? or does it rely more on mental imagery and visuo-spatial abilities? What kind of neural changes happen if someone's mathematical abilities improve through practice? To answer these questions, basic cognitive processes including long term memory, working memory, visuo-spatial perception, number processes are considered through neuropsychological outcomes. Neuronal changes following development and practices are inspected and we can show there are neural networks critical for the mathematical thinking and development: prefrontal-anterior cingulate-parietal network. Through these inquiry, we can infer the answer to our question.

• Korean Journal of Health Education and Promotion
• /
• v.19 no.2
• /
• pp.115-125
• /
• 2002

This study is a investigation research to examine total 123 children's thought, perception and coping method about measles, with 62 children who had experienced the measles and 61 good health children in the school, which had spread to a primary school in kyoungsang-bukdo province. The data collection was done from December 6 to December 8. The analysis of data was SPSS(10.0) for descriptive statistics. The data were collected from total 123 children, 62 of them who had diagnosed measles on October, 2000, when the measles had ended, were used a purposive sampling, the others who had a good health were used a convenience sampling. From three to six grade students made out directly the questionaire in the way of self-questionaire, and from one to two grade students, made out answering the question which the researcher had read the items. The researchers call back the students to complement the contents about the items inadequate answers, so they raised the reliability. The results were as follows. 1. The results of observe carefully the measles infection degree by a sex, the boys(27.4%) were sick severely compared with girls(9.7%)were sick weakly compared with the boys(27.4%)(p〈0.01). 2. The 62.9 percents of infected children by measles thought that they were infected at school, regarded the doctors as a first judge, and had caught the measles because of their fault. The results of observe carefully, 33.8 percents children of infected by measles had have a secondary vaccination. To the question whether they go to institute or not while suffering from the measles, 35.5% children didn't go there since they had heard the fact they infected the measles. 3. To a question of asking if close mend caught the measles, what will they do, 65.1% children of caught the measles answer ‘I can't meet my friend'(p〈0.001). It was significant that infected children have more interests than didn't infected children. The 22% children of didn't catch the measles take great interested in health compare with the 12.2% children of infected the measles(p〈0.05). To the question if they listen the preservation of health broadcasting, 63.4% children answer ‘I listen well’. It was significant between the infected group and didn't infect group(p〈0.05). To the question if they delivery to the written information at home, it was significant between the infected group and didn't infect group(p〈0.05). 4. The infected group of 69.1% children think the health is most important in their life school than any other they like study.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.73-83
• /
• 2011

The question answering system shows the answers that are input by other users for user's question. In spite of many researches to try to enhance the satisfaction level of answers for user question, there is a essential limitation. So, the question answering system provides users with the method of recommendation of another questions that can satisfy user's intention with high probability as an auxiliary function. The method using the fuzzy relational product operator was proposed for recommending the questions that can includes largely the contents of the user's question. The fuzzy relational product operator is composed of the Kleene-Dienes operator to measure the implication degree by contents between two questions. However, Kleene-Dienes operator is not fit to be the right operator for finding a question answers pair that semantically includes a user question, because it was not designed for the purpose of finding the degree of semantic inclusion between two documents. We present a novel fuzzy implication operator that is designed for the purpose of finding question answer pairs by considering implication relation. The new operator calculates a degree that the question semantically implies the other question. We show the experimental results that the probability that users are satisfied with the searched results is increased when the proposed operator is used for recommending of question answering system.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.25-34
• /
• 2020

Community question and answering service is one of the main sources of information and knowledge in the Web. The quality of information in question and answer documents is determined by the clarity of the question and the relevance of the answers, and the readability of a document is a key factor for evaluating the quality. This study is to measure the quality of documents used in community question and answering service. For this purpose, we compare the frequency of occurrence by vocabulary level used in community documents and measure the readability index of documents by institution of author. To measure the readability index, we used the Dale-Chall formula which is calculated by vocabulary level and sentence length. The results show that the vocabulary used in the answers is more difficult than in the questions and the sentence length is longer. The gap in readability between questions and answers is also found by writing institution. The results of this study can be used as basic data for improving online counseling services.