• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.290-292
• /
• 2021

최근 인코더-디코더 구조의 자연어 처리모델이 활발하게 연구가 이루어지고 있다. 인코더-디코더기반의 언어모델은 특히 본문의 내용을 새로운 문장으로 요약하는 추상(Abstractive) 요약 분야에서 널리 사용된다. 그러나 기존의 언어모델은 단일 문서 및 문장을 전제로 설계되었기 때문에 기존의 언어모델에 다중 문장을 요약을 적용하기 어렵고 주제가 다양한 여러 문장을 요약하면 요약의 성능이 떨어지는 문제가 있다. 따라서 본 논문에서는 다중 문장으로 대표적이고 상품 리뷰를 워드 임베딩의 유사도를 기준으로 클러스터를 구성하여 관련성이 높은 문장 별로 인공 신경망 기반 언어모델을 통해 요약을 수행한다. 제안하는 모델의 성능을 평가하기 위해 전체 문장과 요약 문장의 유사도를 측정하여 요약문이 원문의 정보를 얼마나 포함하는지 실험한다. 실험 결과 기존의 RNN 기반의 요약 모델보다 뛰어난 성능의 요약을 수행했다.

• Journal of The Korean Association For Science Education
• /
• v.40 no.2
• /
• pp.163-175
• /
• 2020

The purpose of this study is to propose a method for analyzing suitable achievement standards for the nature of science curriculum. This can be done by introducing various analysis methods, as well as using practical examples to analyze the achievement standards that are the starting point for teaching and learning in the 2015 revised curriculum. In this paper, three methods are shown: ① the method suggested by the Gyeonggido Office of Education, ② the method using understanding verbs of backward design, ③ the method using Bloom's revised taxonomy. In addition, we propose a method to analyze the achievement standards of science curriculum utilizing the characteristics of science curriculum. This method takes advantage of the above three analysis methods. After separating the content and performance verbs, subdividing the performance verbs into the performance verbs of six aspects of understanding and restatement of the achievement standards, the restatement of achievement standards enabled the analysis of in-depth achievement standards by linking to a process-focused assessment plan considering the level of thinking by utilizing the two-dimensional framework of Bloom's revised taxonomy. Through this study, I hope that elementary school teachers will develop meaningful teaching and learning methods that utilize the essence of the subject through in-depth analysis of the achievement standards of science as a subject.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1419-1425
• /
• 2017

The ultimate goal of legal knowledge search is to obtain optimal legal information based on laws and precedent. Text mining research is actively being undertaken to meet the needs of efficient retrieval from large scale data. A typical method is to use a word embedding algorithm based on Neural Net. This paper demonstrates how to search relevant information, applying Korean law information to word embedding. First, we extracts reference laws from precedents in order and takes reference laws as input of Law2Vec. The model learns a law by predicting its surrounding context law. The algorithm then moves over each law in the corpus and repeats the training step. After the training finished, we could infer the relationship between the laws via the embedding method. The search performance was evaluated based on precision and the recall rate which are computed from how closely the results are associated to the search terms. The test result proved that what this paper proposes is much more useful compared to existing systems utilizing only keyword search when it comes to extracting related laws.

• Journal of KIISE:Information Networking
• /
• v.30 no.4
• /
• pp.484-493
• /
• 2003

Proxy signature scheme is a cryptographic protocol that an original signer delegates her signing capability to a proxy signer, and then the proxy signer is able to create signatures on behalf of the original signer. In general, there is time-limit for which the signing capability of the proxy signer is valid. One of methods to limit the valid delegation time is to make public delegation information contain the expiration date of the delegation. however, in this method we cannot prevent the proxy signer from signing after the valid delegation is expired because no one knows the exact time when the proxy signer signed a message. The validity of the past legal signatures cannot be preserved in case that the proxy singer´s key is compromised during the delegation period. In this paper, we propose a new scheme, time-limited forward-secure proxy signature protocol, which prevents the proxy singer from signing after the valid delegation is expired and which preserves the validity of the past legal signatures even if the signing key is compromised. The proposed scheme does not require the exact time-information by making an original signer control time-related parameters and satisfies the forward-security property in each update-period of the proxy signing key. The time-period is determined according to the application characteristics or security policies.

• Journal of Korean Home Economics Education Association
• /
• v.30 no.3
• /
• pp.175-193
• /
• 2018

The course of home economics education is the one that fosters the ability to solve life problems. The life problem is permanent involving the individual, family, and society in overall. Thus, this study was to compose a class which applied the backward design model suggested by Wiggins and McTighe focusing on the usability of it in the educational filed of the home science to overcome the limitation of the education in the filed based on that critical mind. Therefore, this study developed the teaching·learning plan applying the backward design model to the 'Food and Nutrition' unit of the home economics education. It is expected that the unit and the teaching plan are used as materials for the class on the dietary life unit which is meaningful for learners in the educational field of the home economics education.

• The monthly packaging world
• /
• s.251
• /
• pp.97-111
• /
• 2014

한국해사위험물검사원은 위험물 선박운송 및 저장에 따른 재해예방과 기술진흥을 위하여 국내/외 기준제도의 연구개발 및 성과보급에 힘쓰고 있으며, 위험물 종사자에 대한 교육에서부터 적재, 수납, 용기, 포장 등의 위험물 검사를 제공하여 위험물의 안전한 선박운송과 해운, 항만의 건전한 발전에 기여하고자 설립됐다. 본 고에서는 검사원의 정보제공 아래, 위험물의 안전한 해상운송을 도모하고, 위험물의 제조자, 수출입자, 포장업자, 포워드, 운송사 및 선원들에게 도움을 주기 위하여 IMDG Code 36차 개정판의 내용을 요약 정리하여 연재한다.

• The monthly packaging world
• /
• s.252
• /
• pp.106-117
• /
• 2014

한국해사위험물검사원은 위험물 선박운송 및 저장에 따른 재해예방과 기술진흥을 위하여 국내/외 기준제도의 연구개발 및 성과보급에 힘쓰고 있으며, 위험물 종사자에 대한 교육에서부터 적재, 수납, 용기, 포장 등의 위험물 검사를 제공하여 위험물의 안전한 선박운송과 해운, 항만의 건전한 발전에 기여하고자 설립됐다. 본 고에서는 검사원의 정보제공 아래, 위험물의 안전한 해상운송을 도모하고, 위험물의 제조자, 수출입자, 포장업자, 포워드, 운송사 및 선원들에게 도움을 주기 위하여 IMDG Code 36차 개정판의 내용을 요약 정리하여 연재한다.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.5-11
• /
• 1996

The purpose of this paper is to propose a method improving the performance of a semi-continuous hidden Markov model(SCHMM) speaker adaptation system which uses Bayesian Parameter reestimation approach. The performance of Bayesian speaker adaptation could be degraded in case that the features of a new speaker are severely different from those of a reference codebook. The excessive codewords of the reference codebook still remain after adaptation proess. which cause confusion in recognition process. To solve such problems, the proposed method uses formant information which is extracted from the cepstral coefficients of the reference codebook and adaptation data. The reference codebook is adapted to represent the formant distribution of a new speaker and it is used for Bayesian speaker adaptation as an initial codebook. The proposed method provides accurate correspondence between reference codebook and adaptation data. It was observed that the excessive codewords were not selected during recognition process. The experimental results showed that the proposed method improved the recognition performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.11C
• /
• pp.1491-1497
• /
• 2004

The psychoacoustic model in MPEG audio layer-III (MP3) encoder is optimized for the fixed-point processing. The optimization process consists of determining the data word length of arithmetic unit and the algorithm for transcendental functions that are often used in the psychoacoustic model. In order to determine the data word length, we defined a statistical model expressing the relation between the fixed-point operation errors of the psychoacoustic model and the probability of alteration of the allocated bits doe to these errors. Based on the simulations using this model, we chose a 24-bit data path and constructed a 24-bit fixed-point MP3 encoder. Sound quality tests using the constructed fixed-point encoder showed a mean degradation of -0.2 on ITU-R 5-point audio impairment scale.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.119-132
• /
• 2021

Identification of associated knowledge based on content relevance is a fundamental functionality in managing service and security of core knowledge. This study compares the performance of methods to identify associated knowledge based on content relevance, i.e., the associated document network composition performance of keyword-based and word-embedding approach, to examine which method exhibits superior performance in terms of quantitative and qualitative perspectives. As a result, the keyword-based approach showed superior performance in core document identification and semantic information representation, while the word embedding approach showed superior performance in F1-Score and Accuracy, association intensity representation, and large-volume document processing. This study can be utilized for more realistic associated knowledge service management, reflecting the needs of companies and users.