• 한국정보컨버전스학회:학술대회논문집
• /
• 2008.06a
• /
• pp.53-56
• /
• 2008

This paper reports on the ACQA(Animated agent for Conversational Question Answering) project conducted at LIMSI. The aim is to design an expressive animated conversational agent(ACA) for conducting research along two main lines: 1/ perceptual experiments(eg perception of expressivity and 3D movements in both audio and visual channels): 2/ design of human-computer interfaces requiring head models at different resolutions and the integration of the talking head in virtual scenes. The target application of this expressive ACA is a real-time question and answer speech based system developed at LIMSI(RITEL). The architecture of the system is based on distributed modules exchanging messages through a network protocol. The main components of the system are: RITEL a question and answer system searching raw text, which is able to produce a text(the answer) and attitudinal information; this attitudinal information is then processed for delivering expressive tags; the text is converted into phoneme, viseme, and prosodic descriptions. Audio speech is generated by the LIMSI selection-concatenation text-to-speech engine. Visual speech is using MPEG4 keypoint-based animation, and is rendered in real-time by Virtual Choreographer (VirChor), a GPU-based 3D engine. Finally, visual and audio speech is played in a 3D audio and visual scene. The project also puts a lot of effort for realistic visual and audio 3D rendering. A new model of phoneme-dependant human radiation patterns is included in the speech synthesis system, so that the ACA can move in the virtual scene with realistic 3D visual and audio rendering.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.13-21
• /
• 2011

It is not easy to develop the system as the subjective-type evaluation has the difficulty in natural language processing. This thesis designs and implements the automatic evaluation system with natural language processing technique. To solve the degradation of general evaluation system, we define the question type and improve the performance of evaluation through the adaptive process for each question type. To evaluate the system, we analyze the correlation between human evaluation and term-based evaluation, and between human evaluation and this system evaluation. We got the better result than term-based evaluation. It needs to expand the question type and improve the adaptive processing technique for each type.

• The Journal of the Korean dental association
• /
• v.48 no.2
• /
• pp.127-139
• /
• 2010

Objectives : The study explored perceptional gap of dentists and their employees between expectation and satisfaction. Methods : For analysis, the study surveyed 407 employees and 91 dentists on their expectation and satisfaction depending on expectation. Results : When the satisfaction on a question was lower than expectation; the rate of sufficiency was below 100%, it is necessary to improve on the question. Contrarily when the satisfaction on a question was higher than expectation; the rate of sufficiency was upper 100%, it is necessary to continuously support the question. The most of satisfaction of employees on their dentists and their organization were lower than employees's expectation of those. The most of satisfaction of dentists on their own and employees were lower than dentists's expectation of those as similar as employees cases, It means that all of questions need to improve continuously. Conclusions : The issues for prior decision to change these phenomena are 1) improvement of communication each other, 2) recovery of credence each other, and 3) leadership style change from authoritarian to consideration.

• Asia pacific journal of information systems
• /
• v.25 no.4
• /
• pp.686-711
• /
• 2015

The performance of a novel medical question-answering engine called CliniCluster and existing search engines, such as CQA-1.0, Google, and Google Scholar, was evaluated using known-item searching. Known-item searching is a document that has been critically appraised to be highly relevant to a therapy question. Results show that, using CliniCluster, known-items were retrieved on average at rank 2 ($MRR@10{\approx}0.50$), and most of the known-items could be identified from the top-10 document lists. In response to ill-defined questions, the known-items were ranked lower by CliniCluster and CQA-1.0, whereas for Google and Google Scholar, significant difference in ranking was not found between well- and ill-defined questions. Less than 40% of the known-items could be identified from the top-10 documents retrieved by CQA-1.0, Google, and Google Scholar. An analysis of the top-ranked documents by strength of evidence revealed that CliniCluster outperformed other search engines by providing a higher number of recent publications with the highest study design. In conclusion, the overall results support the use of CliniCluster in answering therapy questions by ranking highly relevant documents in the top positions of the search results.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.132-138
• /
• 2022

Due to the impacts of the current pandemic COVID-19 and the continuation of studying online. There is an urgent need for an effective and efficient education platform to help with the continuity of studying online. Therefore, the question bank system (QB) is introduced. The QB system is designed as a website to create a single platform used by faculty members in universities to generate questions and store them in a bank of questions. In addition to allowing them to add two types of questions, to help the lecturer create exams and present the results of the students to them. For the implementation, two languages were combined which are PHP and Python to generate questions by using Artificial Intelligence (AI). These questions are stored in a single database, and then these questions could be viewed and included in exams smoothly and without complexity. This paper aims to help the faculty members to reduce time and efforts by using the Question Bank System by using AI and Natural Language Processing (NLP) to extract and generate questions from given text. In addition to the tools used to create this function such as NLTK and TextBlob.

• The Journal of the Korea Contents Association
• /
• v.4 no.2
• /
• pp.36-42
• /
• 2004

This paper describes the Korean Question answering system using the syntactic-relation information d verbs to overcome lack of reliable knowledge and linguistic resources. The syntactic-relation information consists d the original form d a verb, usual usage pattern, semantic category of each dependent noun, synonym verbs and passive verbs. We use the syntactic-relation information to parse sentences or phrases with usual usage pattern of the verb and semantic conditions of dependent components on the verb. We also use that information to parse answer candidate sentences, and find an answer from questioned case slot. Our experiments that usage of the syntactic-relation information of verbs to mm lack of reliable knowledge and linguistic resources can be utilized efficiently for the Korean question answering system.

• Journal of The Korean Association For Science Education
• /
• v.30 no.6
• /
• pp.799-814
• /
• 2010

This study aimed at developing a set of question cards for fostering deep understanding and encouraging reasoning about fossils and analyze the characteristics of visitors' communication depending on whether to use the question cards in a fossil gallery. Through several steps, a card set consisted of nine generic questions about fossil exhibitions and guidance for using question cards were developed. Data related to visitors' communications were collected from 18 peer groups (from 5th to 9th grade) visiting the fossil gallery of Gwacheon National Science Museum. Visiting groups' interactions were videotape recorded and transcribed. 'Holding time,' the types of 'actions,' and the types of 'conversation' were analysed. Visitors' actions were divided into three categories: ‘look’, 'speech', and 'motion.' Furthermore, visitors' conversations categorized as 'speech' were subdivided into four patterns: 'enumerative,' 'consensual,' 'responsive,' and 'argumentative.' Using the question cards contributes to increase holding time and most of the visiting actions. Most of the conversation patterns also increased except the responsive pattern. In conclusion, using question cards in a fossil gallery could facilitate concentrated and meaningful visits by enhancing active verbal and non-verbal communications between exhibit and visitor or among visitors, encouraging visitors' reasoning about exhibits, and guiding visitors what and how to focus on exhibits.

• 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.

• Korean Journal of Logic
• /
• v.15 no.1
• /
• pp.17-53
• /
• 2012

Some Korean Philosophers has manifested their opinions on Sleeping Beauty problem. For example, Hasuk Song and Namjoong Kim stands for an thirder, while Hanseung Kim for a perspectivistic compatibilist. In order to fill a vacant position, I shall make an argument for halfers in this paper. My presumption is that the probability the question now given to sleeping beauty is the first question among several is greater than thirder's calculated value. Futhermore, I argue that the probability the coin landed heads on condition that the question now given to sleeping beauty is the first question is greater than 1/2.

• The Journal of Korean Association of Computer Education
• /
• v.5 no.2
• /
• pp.49-59
• /
• 2002

There have been many attempts to educationally utilize a computer. As a result, a number of learning programs and testing programs have been developed. Testing programs developed so far are rather focusing on giving learners questions without interactivity. Question givers also have to feed question data into a computer. Therefore, this thesis, firstly, explains how learners themselves feed question data into a computer. Secondly, this thesis explains how to develop such a system that can produce new questions based on the question data fed by learners. This paper also introduces the system environment, which features the test item generation system, and explains the system environment by exemplifying internal modules, a test item bank. Besides, we also describe how to apply this system to educational programs and identify whether it is possible to apply it to a Chinese subject and others.