http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Nonlinear Analysis on the Static and Cyclic Behaviors of UHPC Filled Rectangular Steel Tube Columns
Heng Cai,Fangqian Deng,Yanxiang Yan 대한토목학회 2022 KSCE JOURNAL OF CIVIL ENGINEERING Vol.26 No.3
In this paper, a fiber-based computational model is developed for the nonlinear analysis on the static and cyclic behaviors of ultra-high performance concrete filled rectangular steel tube (UHPCFST) columns. In the computational framework, a simplified compressive constitutive model of UHPC confined by rectangular steel tubes is firstly proposed based on available experimental data. Then, two approaches are adopted for considering the local buckling of steel tubes. The second-order as well as the material nonlinearity are also taken into account. Finally, comparative analyses between the predicted and experimental results of the UHPCFST columns are undertaken to verify the robustness and reliability of the fiber-based model. It is shown that the developed fiber-based modeling technique can predict the structural performance of UHPCFST columns with good satisfaction.
Aspect-Based Sentiment Analysis with Position Embedding Interactive Attention Network
Yan Xiang,Jiqun Zhang,Zhoubin Zhang,Zhengtao Yu,Yantuan Xian 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.5
Aspect-based sentiment analysis is to discover the sentiment polarity towards an aspect from user-generatednatural language. So far, most of the methods only use the implicit position information of the aspect in thecontext, instead of directly utilizing the position relationship between the aspect and the sentiment terms. Infact, neighboring words of the aspect terms should be given more attention than other words in the context. This paper studies the influence of different position embedding methods on the sentimental polarities of givenaspects, and proposes a position embedding interactive attention network based on a long short-term memorynetwork. Firstly, it uses the position information of the context simultaneously in the input layer and theattention layer. Secondly, it mines the importance of different context words for the aspect with the interactiveattention mechanism. Finally, it generates a valid representation of the aspect and the context for sentimentclassification. The model which has been posed was evaluated on the datasets of the Semantic Evaluation 2014. Compared with other baseline models, the accuracy of our model increases by about 2% on the restaurantdataset and 1% on the laptop dataset.