• ETRI Journal
• /
• v.42 no.6
• /
• pp.899-911
• /
• 2020

The data in tables are accurate and rich in information, which facilitates the performance of information extraction and question answering (QA) tasks. TableQA, which is based on tables, solves problems by understanding the table structure and searching for answers to questions. In this paper, we introduce both novice and intermediate Korean TableQA tasks that involve deducing the answer to a question from structured tabular data and using it to build a question answering pair. To solve Korean TableQA tasks, we use S3-NET, which has shown a good performance in machine reading comprehension (MRC), and propose a method of converting structured tabular data into a record format suitable for MRC. Our experimental results show that the proposed method outperforms a baseline in both the novice task (exact match (EM) 96.48% and F1 97.06%) and intermediate task (EM 99.30% and F1 99.55%).

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.285-291
• /
• 2001

This paper describes a natural language question answering system that can be used by students in getting as solution to their queries. Unlike AI question answering system that focus on the generation of new answers, the present system retrieves existing ones from question-answer files. Unlike information retrieval approaches that rely on a purely lexical metric of similarity between query and document, it uses a semantic knowledge base (WordNet) to improve its ability to match question. Paper describes the design and the current implementation of the system as an intelligent tutoring system. Main drawback of the existing tutoring systems is that the computer poses a question to the students and guides them in reaching the solution to the problem. In the present approach, a student asks any question related to the topic and gets a suitable reply. Based on his query, he can either get a direct answer to his question or a set of questions (to a maximum of 3 or 4) which bear the greatest resemblance to the user input. We further analyze-application fields for such kind of a system and discuss the scope for future research in this area.

• 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.

• Journal of Korean Elementary Science Education
• /
• v.36 no.4
• /
• pp.331-345
• /
• 2017

The purpose of this study is to collect and analyze the student's pre-inquire and to obtain information on how to use the teaching-learning process. The specific research problem is to confirm the level of the student's pre-inquire, to identify the characteristics of each type, and to check what pre-inquire can be used in the teaching-learning process. The research was conducted on 149 children in the $3^{rd}$ and $4^{th}$ grade of elementary school, and collected a total of 2,034 inquires. As a result of analyzing three times, the students' pre-inquires accounted for 90% of Level 2 and Level 3, which are the inquires that give meaningful answers in the teaching-learning process. These results show that the pre-inquires presented before the students take up the new lesson are not low-level inquires and they can present meaningful inquires that can be used for teaching-learning. Next, as a result of analyzing the student's inquire by type, the factual question was the largest with 50%, followed by comprehension question, procedural question, application question, and prediction question. The factual and procedural questions showed that they could be used as learning activities during the teaching-learning process. Comprehension questions included in the wonderment question can be used as a learning question. And the application question is a question that can be applied to deepening activities, and the prediction question can be used in the inquiry and experiment process of learning activities.

• Journal of Science Education
• /
• v.34 no.1
• /
• pp.105-112
• /
• 2010

The purpose of this research was to investigate relations between prior knowledge and primary grade science brilliant intellect's observation and inquiry. The subjects were selected 'Spider and cobweb' that self-regulation quest is available. Subjects were divided into two groups with one group having no prior knowledge about research subject. Compared observation method question type and level that appear between subject achievement to group. Target learning group are 5 ~ 6 school year 17 people for national university for the gifted center of local middle city. Researcher collected and analyzed data using summer vacation concentration education period. Source collection subject's research recording paper, subject's voice recording device, interview data etc. A data analysis tool took advantage of observation method that is studied in existing, question type, question level. Research was able to conclude : First, observation of prior knowledge happened than mass of students who many mass of students are few relatively vigorously. Second, primary grade science brilliant intellect students used more mainly manufacturing observation than simplicity observation that use senses regardless of relative quantity of prior knowledge. Third, prior knowledge expressed variety when many mass of students observe operation relatively.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.419-428
• /
• 2009

A question answering (QA) system can be built using multiple QA modules that can individually serve as a QA system in and of themselves. This paper proposes a learnable, strategy-driven QA model that aims at enhancing both efficiency and effectiveness. A strategy is learned using a learning-based classification algorithm that determines the sequence of QA modules to be invoked and decides when to stop invoking additional modules. The learned strategy invokes the most suitable QA module for a given question and attempts to verify the answer by consulting other modules until the level of confidence reaches a threshold. In our experiments, our strategy learning approach obtained improvement over a simple routing approach by 10.5% in effectiveness and 27.2% in efficiency.

• Asia-Pacific Journal of Business
• /
• v.12 no.3
• /
• pp.51-69
• /
• 2021

Purpose - Based on literature studies of movie reviews and movie ratings, this study raised two research questions on the contents of online word of mouth and the number of movie screens as mediator variables. Research question 1 wanted to figure out which topics of word groups had a positive or negative impact on movie ratings. Research question 2 tried to identify the role of the number of movie screens between movie ratings and box office outcomes. Design/methodology/approach - Through R program, this study collected about 82,000 movie reviews and movie ratings posted on Naver's movie website to examine the role of online word of mouths and movie screen counts in 10 movies that were considered commercially unsuccessful with fewer than 2 million viewers despite securing about 1,000 movie screens. To confirm research question 1, topic modeling, a text mining technique, was conducted on movie reviews. In addition, this study linked the movie ratings posted on Naver with information of KOBIS by date, to identify the research question 2. Findings - Through topic modeling, 5 topics were identified. Topics found in this study were largely organized into two groups, the content of the movie (topic 1, 2, 3) and the evaluation of the movie (topics 4, 5). When analyzing the relationship between movie reviews and movie ratings with 5 mediators identified in topic modeling to probe research question 1, the topic word groups related to topic 2, 3 and 5 appeared having a negative effect on the netizen's movie ratings. In addition, by connecting two secondary data by date, analysis for research question 2 was implemented. The outcomes showed that the causal relationship between movie ratings and audience numbers was mediated by the number of movie screens. Research implications or Originality - The results suggested that the information presented in text format was harder to quantify than the information provided in scores, but if content information could be digitalized through text mining techniques, it could become variable and be analyzed to identify causality with other variables. The outcomes in research question 2 showed that movie ratings had a direct impact on the number of viewers, but also had indirect effects through changes in the number of movie screens. An interesting point is that the direct effect of movie ratings on the number of viewers is found in most American films released in Korea.

• 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.

• Journal of the Korean Society for Library and Information Science
• /
• v.49 no.1
• /
• pp.483-511
• /
• 2015

The efficiency and quality of the social reference sites are being challenged because a large quantity of the questions have not been answered or satisfied for quite a long time. Main goal of this study is to investigate important factors that affect the performance of question triage to relevant answerers in the context of social reference. To achieve the goal, expert finding techniques were used to construct an automated question triage approach to resolve this problem. Furthermore, important factors affecting triage decisions in digital reference were first examined, and extended them to the social reference setting by investigating important factors affecting the performance of automated question triage in the social reference setting. The study was conducted using question-answer pairs collected from Ask Metafilter. For the evaluation, logistic regression analyses were conducted to examine which factors would significantly affect the performance of predicting relevant answerers to questions. The results of the current study have important implications for research and practice in automated question triage for social reference. Furthermore, the results will offer insights into designing user-participatory digital reference systems.

• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.927-933
• /
• 2018

One of the factors that have the greatest influence on the error of the question answering system that finds and provides answers to natural language questions is the step of searching for documents or passages that contain correct answers. In order to improve the retrieval performance, it is necessary to understand the characteristics of documents and passages containing correct answers. This paper experimentally analyzes how many question words appear in the correct answer documents, how the location of the question word is distributed, and how the topic of the question and the correct answer document are similar using the corpus composed of the question, the documents with correct answer, and the documents without correct answer. This study explains the causes of previous search research results for question answer system and discusses the necessary elements of effective search step.