http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박천음(Cheoneum Park),이창기(Changki Lee),홍수린(Sulyn Hong),황이규(Yigyu Hwang),유태준(Taejoon Yoo),김현기(Hyunki Kim) Korean Institute of Information Scientists and Eng 2018 정보과학회논문지 Vol.45 No.12
Machine reading comprehension is the task of understanding a given context and identifying the right answer in context. Simple recurrent unit (SRU) solves the vanishing gradient problem in recurrent neural network (RNN) by using neural gate such as gated recurrent unit (GRU), and removes previous hidden state from gate input to improve speed. Self-matching network is used in r-net, and this has a similar effect as coreference resolution can show similar semantic context information by calculating attention weight for its RNN sequence. In this paper, we propose a S²-Net model that add self-matching layer to an encoder using stacked SRUs and constructs a Korean machine reading comprehension dataset. Experimental results reveal the proposed S²-Net model has EM 70.81% and F1 82.48% performance in Korean machine reading comprehension.
정치적 이념에 따른 트위터 공간에서의 집단 간 의견차이 분석
정효정(Hyojung Jung),배정환(Junghwan Bae),홍수린(Sulyn Hong),박찬웅(Chanung Park),송민(Min Song) 한국언론학회 2016 한국언론학보 Vol.60 No.2
In this study, we examine the differences in public opinion posts of Twitter users including a mention on “Sewol ferry accident” in various political stances. We assume the selective exposure theory which states that a connection in Twitter is built between two users who shares similar political stance and the aggregation of all connections constructs a homogeneous network. Besides, twitter users may use the same term in different meaning and context according to their political stances. We apply social network analysis to identify user communities according to political stances and to evaluate the impact of the main players in each community by examining the frequent terms used in the communities. This results in not only structural implications but also semantic implications induced from the different opinions shown across homogeneous networks. Our results show the usefulness of the differences between online groups using network analysis method considering both structural and semantic perspectives. This study is expected to detect different political communities and to become a foundation of semantic network analysis.