• Applied Chemistry for Engineering
• /
• v.5 no.1
• /
• pp.149-159
• /
• 1994

The kinetics and equilibrium of metal extraction by benzamidoxime and phenylacetamidoxime-chloroform were investigated to apply amidoxime to metal extraction as chelating agent. The overall extraction constant extraction mechanism and selective extraction of copper were examined from the relation among extraction ratio, hydrogen ion concentration and extractant concentration. The experimental rate equation of copper extraction coincided with the theoretical rate equation and was expressed as $R_o=k{\overline{C}}_{HRo}(C_{Mo}/C_{Ho})^{1/2}$. The chemical species extracted was found to the type of ${\overline{CuR_2}}$.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.55-60
• /
• 2018

기계학습 기반인 관계추출 모델을 설계할 때 다량의 학습데이터를 빠르게 얻기 위해 원격지도학습 방식으로 데이터를 수집한다. 이러한 데이터는 잘못 분류되어 학습데이터로 사용되기 때문에 모델의 성능에 부정적인 영향을 끼칠 수 있다. 본 논문에서는 이러한 문제를 강화학습 접근법을 사용해 해결하고자 한다. 본 논문에서 제안하는 모델은 오 분류된 데이터로부터 좋은 품질의 데이터를 찾는 문장선택기와 선택된 문장들을 가지고 학습이 되어 관계를 추출하는 관계추출기로 구성된다. 문장선택기는 지도학습데이터 없이 관계추출기로부터 피드백을 받아 학습이 진행된다. 이러한 방식은 기존의 관계추출 모델보다 좋은 성능을 보여주었고 결과적으로 원격지도학습데이터의 단점을 해결한 방법임을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.35-48
• /
• 2017

Extracting temporal information from documents is becoming more important, because it can be used to various applications such as Question-Answering (QA) systems, Recommendation systems, or Information Retrieval (IR) systems. Most previous studies only focus on English documents, and they are not applicable to the other languages due to the inherent characteristics of languages. In this paper, we propose a new system, named ExoTime, designed to extract temporal information from Korean documents. The ExoTime adopts an external Knowledge Base (KB) in order to achieve better prediction performance, and it also applies a bagging method to the temporal relation prediction. We show that the effectiveness of the proposed approaches by empirical results using Korean TimeBank. The ExoTime system works as a part of ExoBrain that is an artificial intelligent QA system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.33-36
• /
• 2019

DDI 추출은 생물 의학 문헌으로부터 약물-약물 상호작용(Drug-Drug Interaction) 관계를 추출하는 작업으로, 기존에 알려지지 않은 인체 내 약물 간의 효과 또는 부작용 정보를 제공하는데 중요한 역할을 한다. 본 연구에서는 PCNN 모델을 활용하여 특징 추출 과정을 자동화하고 약물 개체 간의 구조 정보를 포착해 개체 간 관계를 효율적으로 추출하였으며, 생물 의학 문헌에서 쓰이는 생소한 용어를 보다 풍부하게 표현하기 위해 5가지 버전의 단어 임베딩을 PCNN의 채널로 사용하였다. 본 연구에서 제안하는 MC-PCNN 모델의 성능 평가를 위해 DDI'13 Corpus 데이터를 사용하여 비교 실험을 진행하였으며, 그 결과 기존 연구보다 $F_1$ 점수 기준 최대 2.05%p 향상된 성능을 보이며 DDI 관계 추출에서 효과적인 방법론임을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.597-601
• /
• 2021

주어진 정보를 자연어로 변환하는 작업은 대화 시스템의 핵심 모듈임에도 불구하고 학습 데이터의 제작 비용이 높아 공개된 데이터가 언어에 따라 부족하거나 없다. 이에 본 연구에서는 텍스트-투-그래프(text-to-graph) 작업인 관계 추출에 쓰이는 데이터의 입출력을 반대로 지정하여 그래프-투-텍스트(graph-to-text) 생성 작업에 이용하는 역 관계 추출(reverse relation extraction, RevRE) 기법을 소개한다. 이 기법은 학습 데이터의 양을 늘려 영어 그래프-투-텍스트 작업의 성능을 높이고 지식 묘사 데이터가 부재한 한국어에선 데이터를 재생성한다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.247-250
• /
• 2021

관계추출(Relation Extraction)이란 주어진 문장에서 엔터티간의 관계를 예측하는 것을 목표로 하는 태스크이다. 이를 위해 문장 구조에 대한 이해와 더불어 두 엔터티간의 관계성 파악이 핵심이다. 기존의 관계추출 연구는 영어 데이터를 기반으로 발전되어 왔으며 그에 반해 한국어 관계 추출에 대한 연구는 부족하다. 이에 본 논문은 한국어 문장내의 엔터티 정보에 대한 위치 정보를 활용하여 관계를 예측할 수 있는 방법론을 제안하였으며 이를 다양한 한국어 사전학습 모델(KoBERT, HanBERT, KorBERT, KoELECTRA, KcELECTRA)과 mBERT를 적용하여 전반적인 성능 비교 및 분석 연구를 진행하였다. 실험 결과 본 논문에서 제안한 엔터티 위치 토큰을 사용하였을때의 모델이 기존 연구들에 비해 좋은 성능을 보였다.

• Journal of Life Science
• /
• v.10 no.2
• /
• pp.202-209
• /
• 2000

The factors affecting chemical composition of green tea (Camellia sinensis L.) during extraction process were temperatures and times. The optimum extraction conditions were measured in relation to the changes of chemical compositions from water extracts of green tea (Camellia sinensis L.) under different extraction temperatures (50, 70, 9$0^{\circ}C$) and extraction times (1, 3, 5 minute). The change of color intensity during browning reaction, flavonoid components, contents of total phenols and hydrogen donating activity (reducing activity for $\alpha$, $\alpha$'-diphenyl-$\beta$ -picryhydrazyl) of water extracts form green tea increased as extraction temperatures increased from 50 to 9$0^{\circ}C$ and extraction times prolonged from 1 to 5 min. The contents of important free sugars such as sucrose and glucose slightly increased as the extraction time was prolonged, while little difference in the content of fructose with the prolonged extraction time. Catechins contents extracted from the commercial steamed green tea were increased at higher temperature and longer extraction time. Epigallocatechin (EGC) extracted from 9$0^{\circ}C$ (extraction time 5 min). presented 99.9 mg/g in highest composition of catechin followed by epigallocatechin gallate (EGCg), epicatechin (EC), epicatechin gallate (ECg). The content of vitamin C extracted from green tea was increased about 2 times as the extraction temperature increased from 50 to 9$0^{\circ}C$ and as the extraction time increased from 1 to 5 min. with exception at 9$0^{\circ}C$(extraction time:5 min) which showed less vitamin C content than 7$0^{\circ}C$(extraction time : 3 min) probably due to possible destruction of vitamin C by high temperature.

• Journal of Korean Society of Water and Wastewater
• /
• v.29 no.3
• /
• pp.325-335
• /
• 2015

Concerns about water quality in the Nakdong River have been raised because the Nakdong River will change from a lotic environment to a lentic environmental due to the installation of eight weirs to be constructed as part of the Four Major Rivers Restoration Project. The rapid urbanization and industrialization of the middle and the lower reaches of Nakdong River causes the indiscreet discharge of uncleanly living sewage and industrial wastewater. And the water quality of lower reaches of Nakdong River is getting seriously worse. Owing to the water shortage of Nakdong River and the closing of reaches because of the estuary dyke in the dry season, the velocity of a moving fluid is almost accumulated under 0.03m/sec. Then a pollutant is piled up on the bottom of the river. Polluted sediment is formed and nutrition level of water is increased more and more. The eutrophication state propagated to dark brown or green from eutrophication often comes out. Therefore in this study, we measured Chl. a of chlorophyll sensor (YSI6600V2) and aceton extraction through field observation in the Nakdong River and Samrangjin. And we evaluated the reliability of chlorophyll sensor. In correlation analysis between chlorophyll sensor and aceton extraction, it shows high relation in general. And it also shows high relation among the chlorophyll sensor and aceton extraction of the dominant diatom (Skeletonema costatum), Dinophyta (Prorocentrum minimum) in the Nakdong River estuary by laboratory analysis results.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.4
• /
• pp.289-307
• /
• 2016

This paper introduces a software system and process model for constructing domain-specific relation extraction datasets semi-automatically. The system uses a set of terms such as genes, proteins diseases and so forth as inputs and then by exploiting massive biological interaction database, generates a set of term pairs which are utilized as queries for retrieving sentences containing the pairs from scientific databases. To assess the usefulness of the proposed system, this paper applies it into constructing a genic interaction dataset related to Alzheimer's disease domain, which extracts 3,510 interaction-related sentences by using 140 gene names in the area. In conclusion, the resulting outputs of the case study performed in this paper indicate the fact that the system and process could highly boost the efficiency of the dataset construction in various subfields of biomedical research.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.335-346
• /
• 2008

Causal relations in ontology should be defined based on the inference types necessary to solve problems specific to application as well as domain. In this paper, we present a model to define and extract causal relations for application ontology for Question-Answering (QA) on fault-diagnosis of electronic devices. Causal categories are defined by analyzing generic patterns of QA application; the relations between concepts in the corpus belonging to the causal categories are defined as causal relations. Instances of casual relations are extracted using lexical patterns in the concept definitions of domain, and extended incrementally with information from thesaurus. On the evaluation by domain specialists, our model shows precision of 92.3% in classification of relations and precision of 80.7% in identifying causal relations at the extraction phase.