• Journal of KIISE
• /
• v.43 no.8
• /
• pp.927-932
• /
• 2016

With the explosive increase in the number of online medical documents, the demand for question-answering systems is increasing. Recently, question-answering models based on machine learning have shown high performances in various domains. However, many question-answering models within the medical domain are still based on information retrieval techniques because of sparseness of training data. Based on various information retrieval techniques, we propose an answer snippet retrieval model for question-answering systems of medical documents. The proposed model first searches candidate answer sentences from medical documents using a cluster-based retrieval technique. Then, it generates reliable answer snippets using a re-ranking model of the candidate answer sentences based on various sentence retrieval techniques. In the experiments with BioASQ 4b, the proposed model showed better performances (MAP of 0.0604) than the previous models.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.327-332
• /
• 2010

Word mismatch is the most significant problem that causes low performance in question classification, whose questions consist of only two or three words that expressed in many different ways. So, it is necessary to apply word association in question classification. In this paper, we propose question classification method using translation-based language model, which use word translation probabilities for question-question pair that is learned in the same category. In the experiment, we prove that translation probabilities of question-question pairs in the same category is more effective than question-answer pairs in total collection.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.2
• /
• pp.299-314
• /
• 2006

This study suggests evaluation criteria for the web-based question-answer databases provided by major Korean search portals. In particular, this study suggests evaluation criteria for the relevance of question titles, entire questions, and answer's. The evaluation criteria for the qualify of answers are also developed. Based on these criteria. evaluation of documents from Naver Knowledge-in are performed. The results of this study can be implemented to the development of test collection of question-answer databases. The implications for system designers and web content providers are discussed.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05b
• /
• pp.755-758
• /
• 2010

본 논문에서는 현재 Jazz에서 사용되어지는 화성기법을 Pat Metheny의 작품인 “Question & Answer”를 통해서 알아보았다. D Minor Pentatonic Scale이 선율에 주로 사용된 본 작품은 Intro부분에서는 Quater Voicing이 사용되었다. A 부분에서는 Line Cliche와 D Minor Scale과 D Harmonic Minor Scale의 Diatonic Chord를 사용하였지만 A Aeolian Mode적인 기법이 A부분 셋 번째 단에서 사용되어 Modal적인 분위기도 연출 하였으며 B부분에서는 John Coltrane이 자주 사용하였던 3 Tonic 기법이 사용되면서 동질의 화성이 일정간격으로 움직이는 Constant Structure기법도 사용되었다.

• Journal of Information Management
• /
• v.37 no.2
• /
• pp.137-156
• /
• 2006

To evaluate the performance of the question and answer services provided through the internet portals in Korea, question and answer transcript of four major services were sampled systematically. Using the digital reference evaluation framework, number and types of questions, response rate, timeliness, accuracy for information questions and user satisfaction were measured and analyzed. The level of the service performance is identified and compared. The conclusion includes suggestions for service improvement.

• 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 Sasang Constitutional Medicine
• /
• v.19 no.1
• /
• pp.116-126
• /
• 2007

1. Objectives The purpose of this study is to find out the characteristics about the Sasang Constitution of elementary school students based on the questions that have significant differences. 2. Methods 146 children who have visited Kang-Nam Kyung-Hee Oriental Hospital Sasang Constitution center from Mar. 2003 to May. 2005, were investigated through the questionnaires. These have the categories of 'Diseases and Symptoms', 'Physical characteristics', 'Eating Habit', and etc., were analyzed statistically. 3. Results (1) There are no specific questions that have significant differences about the diseases and symptoms according to the Sasang constitution. (2) In the category of the 'Physical Characteristics', significantly more Soeumin and Soyangin showed positive answer to the question, 'Thin in some degree' than Taeumin, and significantly more Taeumin showed positive answer to the question, 'Fat in some degree' than the other groups, and significantly more Taeumin showed positive answer to the question, 'Bulging belly' than the Soeumin. (3) In the category of 'Eating Habit', significantly more Soeumin, Soyangin answered positively to 'eating little food(light eating)' than Taeumin, and more Taeumin showed positive answer to 'a lot of food uptake' than the other groups, and significantly more Soeumin to 'eating slowly' than Taeumin, in contrast, significantly more Taeumin showed positive answer to 'eating food in haste and hurry' than the Soeumin, and significantly more Soeumin showed positive answer to the question, 'unwillingness to eat vegetable' than Soyangin, and significantly more Soeumin showed that to the question, 'unbalanced diet' than the other groups, significantly more Taeumin showed positive answer to 'preference for fatty food' than the other groups.

• 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.

• Journal of The Korean Association of Information Education
• /
• v.14 no.3
• /
• pp.405-416
• /
• 2010

Knowledge search system is to find the question-answer documents for user question. Even highly qualified question-answer documents could be far different from those that a user want to find. The reason for this failure is that user frequently fails to make user's question to express his/her intension precisely. In this paper, we show our newly developed knowledge search system that recommends additional question-answer documents to include the contents that user want to find with high probability.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.205-213
• /
• 2024

This study uses a large language model (LLM) to identify Aristotle's rhetorical principles (ethos, pathos, and logos) in COVID-19 information on Naver Knowledge-iN, South Korea's leading question-and-answer community. The research analyzed the differences of these rhetorical elements in the most upvoted answers with random answers. A total of 193 answer pairs were randomly selected, with 135 pairs for training and 58 for testing. These answers were then coded in line with the rhetorical principles to refine GPT 3.5-based models. The models achieved F1 scores of .88 (ethos), .81 (pathos), and .69 (logos). Subsequent analysis of 128 new answer pairs revealed that logos, particularly factual information and logical reasoning, was more frequently used in the most upvoted answers than the random answers, whereas there were no differences in ethos and pathos between the answer groups. The results suggest that health information consumers value information including logos while ethos and pathos were not associated with consumers' preference for health information. By utilizing an LLM for the analysis of persuasive content, which has been typically conducted manually with much labor and time, this study not only demonstrates the feasibility of using an LLM for latent content but also contributes to expanding the horizon in the field of AI text extraction.