• 전자공학회논문지 IE
• /
• v.45 no.4
• /
• pp.68-73
• /
• 2008

In this research, we proposed a learner tailoring question recommendation system for web based learning evaluation system. For teaming evaluation process, this system used the item difficulty Each question was stored and managed to the question bank. Item difficulty was recalculated during teaming process and feedback in next course. For learner tailoring question recommendation, learner could choice the teaming part and set the learning difficulty. In application result of proposal method, almost learner could improve learning score by controling teaming difficulty.

• Journal of applied mathematics & informatics
• /
• v.8 no.1
• /
• pp.253-260
• /
• 2001

In this paper we suggest a conditional unrelated question randomized response model by using the Carr et. al.’s model(1982) and Greenberg et. al.’s model(1969). Our model can obtain more comprehensive information about the sensitive character A. We suggest the conditions that make our model efficient compared with models of Greenberg et. al. and Carr et al..

• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.27-38
• /
• 1995

In the surveys of sensitive issues of the population that is composed of several unknown-size stratum, we propose the unrelated question model with quantitative attribute by using stratified double sampling. And, we consider two types of sample allocations under the fixed cost, which are the proportional allocation, the optimum allocation. In efficiency, the proosed model is inferior to the unrelated question model with quantitative attribute by stratified sampling in case of the size of each stratum is known. But we find that efficiency of the proposed model is increased, when the selecting probability of sensitive question p is small and first stage sample size n' is large.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.239-246
• /
• 2020

Recently, Linked Open Data has become a large set of knowledge bases. Therefore, the need to query Linked Data using question answering (QA) techniques has attracted the attention of many researchers. A QA system translates natural language questions into structured queries, such as SPARQL queries, to be executed over Linked Data. The two main challenges in such systems are lexical and semantic gaps. A lexical gap refers to the difference between the vocabularies used in an input question and those used in the knowledge base. A semantic gap refers to the difference between expressed information needs and the representation of the knowledge base. In this paper, we present a novel method using an ontology lexicon and dependency parse trees to overcome lexical and semantic gaps. The proposed technique is evaluated on the QALD-5 benchmark and exhibits promising results.

• Phonetics and Speech Sciences
• /
• v.5 no.4
• /
• pp.121-128
• /
• 2013

In Korean, wh-question and indefinite yes-no questions have the same morphemic and syntactic structure. In speech, however, these two types of questions are distinguished by a prosodic difference. In this study, we examined if Chinese Korean leaners can distinguish between these two types of questions in production and if they can correctly perceive the different meaning of a question based on the prosodic information. For this purpose, we analysed two types of interrogative sentences produced by 5 native speakers and 15 Chinese Korean language leaners. The results show that the 5 Korean native speakers produce two types of questions by a salient prosodic difference, i.e., difference of prosodic structure, different pitch range of wh-phrase and indefinite phrase, and different boundary tone. However, for the 15 Chinese speakers, the two types of questions were not distinguished by the same prosodic features but in the perception analysis they were able to distinguish between the two types of questions easily.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.319-330
• /
• 2021

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.71-74
• /
• 2006

The purpose of this study is to observe how Korean listeners detect a target phoneme with 'Focus' represented by prosodic prominence and question-induced semantic emphasis. According to the automated phoneme detection task using E-Prime, Korean listeners detected phoneme targets more rapidly when the target-bearing words were in prominence position and in question-induced position. However, when phoneme targets were in prominence position, response time was much faster than in question-induced position. The results suggest that the prosodic prominence which is explicit method of focus representation be more effective than question-inducing, implicit method of it, in phoneme detecting.

• 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.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.11-21
• /
• 2024

We focus on open-domain question-answering tasks that involve a chain-of-reasoning, which are primarily implemented using large language models. With an emphasis on cost-effectiveness, we designed EffiChainQA, an architecture centered on the use of small language models. We employed a retrieval-based language model to address the limitations of large language models, such as the hallucination issue and the lack of updated knowledge. To enhance reasoning capabilities, we introduced a question decomposer that leverages a generative language model and serves as a key component in the chain-of-reasoning process. To generate training data for our question decomposer, we leveraged ChatGPT, which is known for its data augmentation ability. Comprehensive experiments were conducted using the HotpotQA dataset. Our method outperformed several established approaches, including the Chain-of-Thoughts approach, which is based on large language models. Moreover, our results are on par with those of state-of-the-art Retrieve-then-Read methods that utilize large language models.

• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.415-421
• /
• 1998

In this paper, we proposed improved unrelated question model which has the benefit of simplicity the Kim et al.'s two-stage unrelated question model(1992). conditions are obtained under which the proposed model is more efficient than the Greenberg et al. model(1971) and Kim et al's two-stage unrelated question model.