藏文命名实体识别是藏语自然语言处理的基础任务,是完成机器翻译、网络舆情检测和知识图谱构建等任务的前提.传统的基于深度学习的藏文命名实体识别将藏文音节(字嵌入)作为模型输入的方法容易忽略藏文音节的局部特征.针对这一问题,本文...藏文命名实体识别是藏语自然语言处理的基础任务,是完成机器翻译、网络舆情检测和知识图谱构建等任务的前提.传统的基于深度学习的藏文命名实体识别将藏文音节(字嵌入)作为模型输入的方法容易忽略藏文音节的局部特征.针对这一问题,本文提出了一种融合构成藏文音节部件特征和藏文音节特征的藏文命名实体识别神经网络模型SL-BiLSTM-CRF(syllable level long short-term memory conditional random field).其中,SL模块对构成音节的部件信息和藏文的单个音节进行特征编码,将两种不同模态的特征融合之后送入BiLSTM模型进行特征提取并预测实体标签,再通过CRF对BiLSTM模型的预测结果进行矫正,最终输出藏文实体识别结果.实验证明,该方法在藏文命名实体识别任务中相比基于单个藏文音节(字嵌入)的BiLSTM-CRF模型的F_(1)值提高了1.58个百分点,验证了该方法在藏文命名实体识别任务中的有效性.展开更多
Due to the practical problems of the high costs and the long development cycle of China’s cabinet production,a computer-aided design method of the cabinet based on style imagery is proposed.According to the principle...Due to the practical problems of the high costs and the long development cycle of China’s cabinet production,a computer-aided design method of the cabinet based on style imagery is proposed.According to the principle of the conjoint analysis method, the rough set theory and the weight coefficient of different components of the cabinet,a multi-dimensional model of style imagery to evaluate the cabinet is built. Then the related constants of style imagery are calculated and the cabinet components library is also built by the three-dimensional modeling.Finally,with recombinant technology and the mapping model between cabinet style and external characteristics,the prototype system based on Visual Studio is proposed.This system actualizes the bidirectional reasoning between product style imagery and the shape features,which can assist designers to produce more creative designs,greatly improve the efficiency of cabinet development and increase the profits of companies.展开更多
Waste plastics mainly come from MSW and usually exist in the form of mixed plastics. During the co-pyrolysis process of mixed plastics, various plastic components have different physicochemical properties and reaction...Waste plastics mainly come from MSW and usually exist in the form of mixed plastics. During the co-pyrolysis process of mixed plastics, various plastic components have different physicochemical properties and reaction mechanisms. Considering the high viscosity and low thermal conductivity of molten plastics, a falling film pyrolysis reactor was selected to explore the rapid co-pyrolysis process of typical plastic components(PP, PE and PS).The oil and gas yields and the compositions of pyrolysis products of the three components under different ratios at pyrolysis temperatures were analyzed to explore the co-pyrolysis characteristics of PP, PE, and PS. The study is of great significance to the recycling of waste plastics.展开更多
A pair of northeast-southwest-tilted mid-tropospheric ridges and troughs on the continental scale was observed to be the key circulation feature common among wintertime extensive and persistent low tempera-ture events...A pair of northeast-southwest-tilted mid-tropospheric ridges and troughs on the continental scale was observed to be the key circulation feature common among wintertime extensive and persistent low tempera-ture events (EPLTE) in China.During the persistence of such anomalous circulations,the split flow over the inner Asian continent and the influent flow over the southeast-ern coast of China correspond well to the expanded and amplified Siberian high with tightened sea level pressure gradients and hence,a strong,cold advection over south-eastern China.The western Pacific subtropical high tends to expand northward during the early stages of most EPLTEs.展开更多
In this paper, we proposed a registration method by combining the morphological component analysis(MCA) and scale-invariant feature transform(SIFT) algorithm. This method uses the perception dictionaries,and combines ...In this paper, we proposed a registration method by combining the morphological component analysis(MCA) and scale-invariant feature transform(SIFT) algorithm. This method uses the perception dictionaries,and combines the Basis-Pursuit algorithm and the Total-Variation regularization scheme to extract the cartoon part containing basic geometrical information from the original image, and is stable and unsusceptible to noise interference. Then a smaller number of the distinctive key points will be obtained by using the SIFT algorithm based on the cartoon part of the original image. Matching the key points by the constrained Euclidean distance,we will obtain a more correct and robust matching result. The experimental results show that the geometrical transform parameters inferred by the matched key points based on MCA+SIFT registration method are more exact than the ones based on the direct SIFT algorithm.展开更多
文摘藏文命名实体识别是藏语自然语言处理的基础任务,是完成机器翻译、网络舆情检测和知识图谱构建等任务的前提.传统的基于深度学习的藏文命名实体识别将藏文音节(字嵌入)作为模型输入的方法容易忽略藏文音节的局部特征.针对这一问题,本文提出了一种融合构成藏文音节部件特征和藏文音节特征的藏文命名实体识别神经网络模型SL-BiLSTM-CRF(syllable level long short-term memory conditional random field).其中,SL模块对构成音节的部件信息和藏文的单个音节进行特征编码,将两种不同模态的特征融合之后送入BiLSTM模型进行特征提取并预测实体标签,再通过CRF对BiLSTM模型的预测结果进行矫正,最终输出藏文实体识别结果.实验证明,该方法在藏文命名实体识别任务中相比基于单个藏文音节(字嵌入)的BiLSTM-CRF模型的F_(1)值提高了1.58个百分点,验证了该方法在藏文命名实体识别任务中的有效性.
基金The National Natural Science Foundation of China(No.71271053)the Scientific Innovation Research of College Graduates in Jiangsu Province(No.CXLX13_082)
文摘Due to the practical problems of the high costs and the long development cycle of China’s cabinet production,a computer-aided design method of the cabinet based on style imagery is proposed.According to the principle of the conjoint analysis method, the rough set theory and the weight coefficient of different components of the cabinet,a multi-dimensional model of style imagery to evaluate the cabinet is built. Then the related constants of style imagery are calculated and the cabinet components library is also built by the three-dimensional modeling.Finally,with recombinant technology and the mapping model between cabinet style and external characteristics,the prototype system based on Visual Studio is proposed.This system actualizes the bidirectional reasoning between product style imagery and the shape features,which can assist designers to produce more creative designs,greatly improve the efficiency of cabinet development and increase the profits of companies.
基金Supported by the National Natural Science Foundation of China(51503154,51776141)Major Projects of China Water Pollution Control and Treatment Science and Technology(2017ZX07202005)
文摘Waste plastics mainly come from MSW and usually exist in the form of mixed plastics. During the co-pyrolysis process of mixed plastics, various plastic components have different physicochemical properties and reaction mechanisms. Considering the high viscosity and low thermal conductivity of molten plastics, a falling film pyrolysis reactor was selected to explore the rapid co-pyrolysis process of typical plastic components(PP, PE and PS).The oil and gas yields and the compositions of pyrolysis products of the three components under different ratios at pyrolysis temperatures were analyzed to explore the co-pyrolysis characteristics of PP, PE, and PS. The study is of great significance to the recycling of waste plastics.
基金supported by the National Key Technologies R&D Program of China (Grant No.2009BAC51B02)
文摘A pair of northeast-southwest-tilted mid-tropospheric ridges and troughs on the continental scale was observed to be the key circulation feature common among wintertime extensive and persistent low tempera-ture events (EPLTE) in China.During the persistence of such anomalous circulations,the split flow over the inner Asian continent and the influent flow over the southeast-ern coast of China correspond well to the expanded and amplified Siberian high with tightened sea level pressure gradients and hence,a strong,cold advection over south-eastern China.The western Pacific subtropical high tends to expand northward during the early stages of most EPLTEs.
基金the National Science Foundation of China(No.61471185)the Natural Science Foundation of Shandong Province(No.ZR2016FM21)+1 种基金Shandong Province Science and Technology Plan Project(No.2015GSF116001)Yantai City Key Research and Development Plan Project(Nos.2014ZH157 and2016ZH057)
文摘In this paper, we proposed a registration method by combining the morphological component analysis(MCA) and scale-invariant feature transform(SIFT) algorithm. This method uses the perception dictionaries,and combines the Basis-Pursuit algorithm and the Total-Variation regularization scheme to extract the cartoon part containing basic geometrical information from the original image, and is stable and unsusceptible to noise interference. Then a smaller number of the distinctive key points will be obtained by using the SIFT algorithm based on the cartoon part of the original image. Matching the key points by the constrained Euclidean distance,we will obtain a more correct and robust matching result. The experimental results show that the geometrical transform parameters inferred by the matched key points based on MCA+SIFT registration method are more exact than the ones based on the direct SIFT algorithm.
