• Journal of The Korean Association For Science Education
• /
• v.27 no.1
• /
• pp.84-92
• /
• 2007

The purpose of this study was to investigate biologists' brain activation patterns during the generation of scientific questions on biological phenomena. Eight right-handed healthy biologists volunteered to be participants in the present study. The question-generation tasks were presented in a block design. The BOLD signals of the biologists' brain were measured by 3.0T fMRI system and data were analyzed using Statistical Parametric Mapping (SPM2). According to our results, the left inferior and middle frontal gyri, the medial prefrontal cortex, the bilateral hippocampus, the occipito-parietal route, the fusiform gyrus, and the cerebellum were activated significantly during the generation of scientific questions. Therefore, we suggested that generating scientific question is associated with analyzing observed situations, using verbal strategy, retrieving episodic memories for comparisons, and feeling cognitive conflicts.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.81-88
• /
• 2024

Despite the rapid growth of the generative AI market and significant interest from domestic companies and institutions, concerns about the provision of inaccurate information and potential information leaks have emerged as major factors hindering the adoption of generative AI. To address these issues, this paper designs and implements a question-answering system based on the Retrieval-Augmented Generation (RAG) architecture. The proposed method constructs a knowledge database using Korean sentence embeddings and retrieves information relevant to queries through optimized searches, which is then provided to the generative language model. Additionally, it allows users to directly manage the knowledge database to efficiently update changing business information, and it is designed to operate in a private network to reduce the risk of corporate confidential information leakage. This study aims to serve as a useful reference for domestic companies seeking to adopt and utilize generative AI.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• Journal of the Korean earth science society
• /
• v.27 no.1
• /
• pp.20-31
• /
• 2006

This study analysed student teachers' notable questions about the earth science contents in the elementary science textbooks. The contents of notable questions were defined as ‘notable question contents 1' and 'notable question contents 2'. Both the question contorts are contents about which the number of questions is above three times and from two times to three times as much as the mean number of questions per page of each unit respectively. The results are as follows. First, question contents 1 are found as 'clouds observation', 'geological strata formation' and so on. Question contents 2, 'rainfall measurement', 'moon's movement during one night' and so on are found. Second, the number of interrelationships of main terms in questions increased in each question of question contents 1, but 4 term-patterns are found more in question contents 2 than question contents 1. Third, high interrelationship patterns of terms in question contents 1 are 'coal and petroleum-generation', 'metamorphosis-heat and pressure', 'metamorphosis-heat and pressure-metamorphic rocks', 'planet-sun-comet-revolution' and in question contents 2. 'constellation plate-use', 'dryness and wetness hygrometer-principle', 'seismograph-principle-earthquake', 'earth rotation axis-tilting-occurrence', 'dryness and wetness hygrometer-principle-humidity' and so on. The sources of questions analysed in this study are estimated as the content construction system of textbooks, or students' general questions about the earth science contents. If this is the former, the problems in texts and illustrations in textbooks should be articulated and resolved. And if the latter, the elementary science curriculum has to be reconsidered in view of scientific literacy in earth science.

• 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.

• Clinical and Experimental Pediatrics
• /
• v.54 no.3
• /
• pp.106-110
• /
• 2011

In pediatric patients with acute lymphoblastic leukemia (ALL), the Philadelphia chromosome translocation is uncommon, with a frequency of less than 5%. However, it is classified as a high or very high risk, and only 20-30% of Philadelphia chromosome-positive (Ph+) children with ALL are cured with chemotherapy alone. Allogeneic hematopoietic stem cell transplantation from a closely matched donor cures 60% of patients in first complete remission. Recent data suggest that chemotherapy plus tyrosine kinase inhibitors (TKIs) may be the initial treatment of choice for Ph+ ALL in children. However, longer observation is required to determine whether long-term outcome with intensive imatinib and chemotherapy is indeed equivalent to that with allogeneic related or alternative donor hematopoietic stem cell transplantation (HSCT). Reports on the use of second-generation TKIs in children with Ph+ ALL are limited. A few case reports have indicated the feasibility and clinical benefit of using dasatinib as salvage therapy enabling HSCT. However, more extensive data from clinical trials are needed to determine whether the administration of second-generation TKIs in children is comparable to that in adults. Because Ph+ ALL is rare in children, the question of whether HSCT could be a dispensable part of their therapy may not be answered for some time. An international multicenter study is needed to answer the question of whether imatinib plus chemotherapy could replace sibling allogeneic HSCT in children with Ph+ ALL.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.339-346
• /
• 2017

There is increasing interest in text analysis based on unstructured data such as articles and comments, questions and answers. This is because they can be used to identify, evaluate, predict, and recommend features from unstructured text data, which is the opinion of people. The same holds true for TEL, where the MOOC service has evolved to automate debating, questioning and answering services based on the teaching-learning support system in order to generate question topics and to automatically classify the topics relevant to new questions based on question and answer data accumulated in the system. Therefore, in this study, we propose topic modeling using LDA to automatically classify new query topics. The proposed method enables the generation of a dictionary of question topics and the automatic classification of topics relevant to new questions. Experimentation showed high automatic classification of over 0.7 in some queries. The more new queries were included in the various topics, the better the automatic classification results.

• Journal of Digital Convergence
• /
• v.10 no.5
• /
• pp.167-175
• /
• 2012

The purpose of this paper is a study of the next generation innovation to deal with changing business environment in which the competition is getting fierce. The ultimate goal of a company is to sustain and grow by creating value or profit continuously. As the social or business environment changes, the way of creating profits also changes. Therefore, business management or innovation should be evolved in accordance with the value change, and this gives basis to the question "What would the next generation innovation be like?". This paper is not to give the definite answer to the next generation innovation, but to get discussion started. We hope that many ideas, critiques and opinions to this paper will make the next generation innovation clear.

• Journal of Home Health Care Nursing
• /
• v.23 no.1
• /
• pp.34-44
• /
• 2016

Purpose: This study investigated the factors associated with suicidal ideation in the Korean Echo Generation using 2012 Korea Health Panel Data. Methods: The 2012 Korea Health Panel Data were collected from February 2012 to July 2012 and included 2,303 people who responded to a question asking whether they had experienced suicidal ideation. The data were analyzed by chi-square and multiple logistic regression test using SPSS 22.0. Results: The rate of suicidal ideation was 4.2% in the Echo Generation. Factors associated with suicidal ideation in the Echo Generation revealed that the following variables increased the rate of suicidal ideation: sex(odd ratio: 2.39, CI: 1.39-4.09), education(odd ratio: 1.95, CI: 1.08-3.52), depression(odd ratio: 12.06, CI: 6.92-21.03), frustrating experience(odd ratio: 2.52, CI: 1.22-5.20), anxiety about the future(odd ratio: 14.58, CI: 3.20-66.41), self-rated health status(odd ratio: 2.39, CI: 1.39-4.09 and odd ratio: 6.41, CI 2.87-14.33). Conclusion: This study provides a preliminary examination of the factors associated with suicidal ideation in the Echo Generation. A more careful examination may be warranted.