http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
한기종(Han Kijong) 한국가족법학회 2007 가족법연구 Vol.21 No.2
There are many identical historical and cultural backgrounds between South and North Korea and between Taiwan and mainland China, respectively, while these regions are very particular in this modern society in that interruptions or restrictions of life-sphere are being prevailed due to the political issue. Specially, such interruptions or restrictions have been occurred for long time enough to generate many separated-couples. Thus, it has been very imperative that the legal treatment of the separated-couple has to be proceeded at the present time when such interruptions or restrictions are being gradually alleviated in these regions. It can be said that this kind of conflict between legal systems of both parties is brought about by political conflicts between both parties, however, it becomes a compelling subject to solve the problems caused by differences in legal systems between both parties, considering that human rights of both parties must be protected. For this end, the legal systems related to this issue are being improved in these regions.<BR> This study is aiming to obtain a clue for effective legal treatment of marital relations of the separated-couple between South and North Korea, based on the leading case of legal treatment on marital relations of the separated-couple between Taiwan and mainland China. Specifically, this study is not only focused on understanding the general trends of this matter but also on examining the latent issue that can be occurred from this matter, with the view of the comparative method rather than a practical settlement of this matter.
CNN 기반 관계 추출 모델의 성능 향상을 위한 다중-어의 단어 임베딩 적용
남상하(Sangha Nam),한기종(Kijong Han),김은경(Eun-kyung Kim),권성구(Sunggoo Kwon),정유성(Yoosung Jung),최기선(Key-Sun Choi) Korean Institute of Information Scientists and Eng 2018 정보과학회논문지 Vol.45 No.8
The relation extraction task is to classify a relation between two entities in an input sentence and is important in natural language processing and knowledge extraction. Many studies have designed a relation extraction model using a distant supervision method. Recently the deep-learning based relation extraction model became mainstream such as CNN or RNN. However, the existing studies do not solve the homograph problem of word embedding used as an input of the model. Therefore, model learning proceeds with a single embedding value of homogeneous terms having different meanings; that is, the relation extraction model is learned without grasping the meaning of a word accurately. In this paper, we propose a relation extraction model using multi-sense word embedding. In order to learn multi-sense word embedding, we used a word sense disambiguation module based on the CoreNet concept, and the relation extraction model used CNN and PCNN models to learn key words in sentences.