• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.31-35
• /
• 2021

기계독해 시스템은 주어진 질문에 대한 답변을 문서에서 찾아 사용자에게 제공해주는 질의응답 작업 중 하나이다. 기존의 기계독해는 대부분 문서에 존재하는 짧고 간결한 답변 추출 문제를 풀고자 했으며 최근엔 불연속적인 범위를 추출하는 등의 확장된 문제를 다루는 데이터가 공개되었다. 불연속적인 답변 추출은 실제 애플리케이션에서 사용자에게 정보를 유연하게 제공해줄 수 있다. 따라서 본 논문에서는 기존의 간결한 단일 범위 추출에서 확장된 다중 범위 추출 시스템을 제안하고자 한다. 제안 모델은 문서를 구성하는 모든 토큰의 조합으로 구성된 Span Matrix를 통하여 다중 범위 추출 문제를 해결하고자 하며 실험을 통해 기존 연구들과 비교하여 가장 높은 86.8%의 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.568-570
• /
• 2021

기계독해 시스템은 주어진 질문에 대한 답변을 문서에서 찾아 사용자에게 제공해주는 질의응답 작업 중 하나이다. 하지만 대부분의 기계독해 데이터는 간결한 답변 추출을 다루며, 이는 실제 애플리케이션에서 유용하지 않을 수 있다. 실제 적용 단계에서는 짧고 간결한 답변 뿐 아니라 사용자에게 자세한 정보를 제공해줄 수 있는 긴 길이의 답변 제공도 필요하다. 따라서 본 논문에서는 짧은 답변과 긴 답변 모두 추출할 수 있는 모델을 제안한다. 실험을 통해 Baseline과 비교하여 짧은 답변 추출에서는 F1 score 기준 0.7%, 긴 답변 추출에는 1.4%p의 성능 향상을 보이는 결과를 얻었다.

• Journal of Drive and Control
• /
• v.15 no.3
• /
• pp.96-101
• /
• 2018

• Proceedings of the Korean Biophysical Society Conference
• /
• 2002.06b
• /
• pp.13-13
• /
• 2002

기계학습(maching learning)은 경험을 통한 테이터 관측으로부터 스스로 성능을 향상할 수 있는 컴퓨터를 연구하는 인공지능(artificial intelligence)의 한 연구분야이다. 최근 들어 기계학습은 Bioinformatics 분야에서 생명과학 데이터마이닝을 위한 하나의 핵심기술로 부상하고 있다.(중략)

• Journal of the KSME
• /
• v.57 no.3
• /
• pp.34-37
• /
• 2017

이 글은 공학시스템 고장예지 및 건전성 관리 기술을 소개하고, 최근 주목받고 있는 인공지능기술인 딥러닝과 접목한 연구 사례를 제시한다.

• 발명특허
• /
• v.5 no.3 s.49
• /
• pp.5-7
• /
• 1980

• Journal of The Korean Association of Information Education
• /
• v.26 no.5
• /
• pp.407-416
• /
• 2022

Although environmental education has been more important due to global extreme weather and natural desasters, environmental topics are covered by several other subjects because it is not an independent subject in elementary school and they need to distribute more class hours to cover proper amount of environmental content. This study is performed to develop method to integrate environmental education and software education in elementary school. This method helps students to learn topics about recycling by using Artificial Intelligence programming and Artificial Intelligence also helps students to practice recycling in virtual reality. A new teaching and learning module(Problem Recognition→Machine Learning↔Use of AI→Collaboration) is adopted for the learning procedure and more than 80 % of the students replied positively to the survey about the interest on integrated learning, understanding of environmental education, understanding of Artificial Intelligence, further learning on Artificial Intelligence programming.

• Journal of the Korean Society for information Management
• /
• v.34 no.4
• /
• pp.321-344
• /
• 2017

Research on automatic classification of records and documents has been conducted for a long time. Recently, artificial intelligence technology has been developed to combine machine learning and deep learning. In this study, we first looked at the process of automatic classification of documents and learning method of artificial intelligence. We also discussed the necessity of applying artificial intelligence technology to records management using various cases of machine learning, especially supervised methods. And we conducted a test to automatically classify the public records of the Seoul metropolitan government into BRM using ETRI's Exobrain, based on supervised machine learning method. Through this, we have drawn up issues to be considered in each step in records management agencies to automatically classify the records into various classification schemes.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.8
• /
• pp.67-73
• /
• 2021

In this study, we installed forward and reverse rotation rotavators on a tractor to measure the load in the field and analyze the power consumed. The rotavator is attached to the rear of the tractor and transmits the power applied from the power take off (PTO) of the tractor to the rotating shaft of the rotavator, and it plows or reverses the soil according to the rotational direction of the rotating shaft. Depending on the rotational direction of the rotavator, the power consumed in the tractor engine and the power transmitted to the tractor axle and rotavator also vary, thus, research of load and power is an essential factor in designing the system. As a field test results, 84.1-93.5% power was consumed by the forward rotation rotavator, and 37.8-57.5% power was consumed by the reverse rotation rotavator. In addition, depending on the rotation direction of the rotavator, the power consumed by the tractor was in the order of PTO and axle. Based on the research results, development of reliable rotavator systems would be possible in the future research.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.5
• /
• pp.885-892
• /
• 2018

A series of revolutionary industrial changes took place from the 18th century of the First Industrial Revolution. The fourth industrial revolution is a new industrial revolution in which intelligence and information unite. Social, cultural, economic and educational systems are expected to emerge within the category of access and experience. In the course of intelligent mechanization, manpower and machinery need to be commandeered. Tools should be left to the machine and humans should look at essential issues. In the 4th Industrial Revolution, the paradigm of education should fundamentally change. Instead of routine technologies based on memorization, one should learn how to access and utilize. It needs to focus on areas of debate, cooperation, communication, sensibility, and artistry that robots and artificial intelligence can not afford. The fourth industrial revolution is the fusion of human beings and technology, the humanities and the technology.