This letter presents a new chunking method based on Maximum Entropy (ME) model with N-fold template correction model.First two types of machine learning models are described.Based on the analysis of the two models,the...This letter presents a new chunking method based on Maximum Entropy (ME) model with N-fold template correction model.First two types of machine learning models are described.Based on the analysis of the two models,then the chunking model which combines the profits of conditional probability model and rule based model is proposed.The selection of features and rule templates in the chunking model is discussed.Experimental results for the CoNLL-2000 corpus show that this approach achieves impressive accuracy in terms of the F-score:92.93%.Compared with the ME model and ME Markov model,the new chunking model achieves better performance.展开更多
Plans for the Silk Road Economic Belt （SREB） include construction of two axes, two belts and two radiated areas. As a significant national strategy for China, the emphasis is on the construction of roads and achievi...Plans for the Silk Road Economic Belt （SREB） include construction of two axes, two belts and two radiated areas. As a significant national strategy for China, the emphasis is on the construction of roads and achieving economic agglomeration and radiation through the construction of traffic axes. Using published literature and data analyses, this paper studied current traffic patterns between China and other regions within the SREB from the perspective of rail, ocean and air transportation. With regard to existing problems and development prospects of these three types of transportation, we propose construction modes for the traffic economic belt across continental plates and that future construction within the SREB should consider key cities as joints and arterial traffic lines as development axes, promote connecting of joints by lines, advance deep construction through joints and axes, connect lines into net, and develop informationalized traffic economic belt on the basis of trans-regional cooperation.展开更多
基金Supported by National Natural Science Foundation of China (No.60504021).
文摘This letter presents a new chunking method based on Maximum Entropy (ME) model with N-fold template correction model.First two types of machine learning models are described.Based on the analysis of the two models,then the chunking model which combines the profits of conditional probability model and rule based model is proposed.The selection of features and rule templates in the chunking model is discussed.Experimental results for the CoNLL-2000 corpus show that this approach achieves impressive accuracy in terms of the F-score:92.93%.Compared with the ME model and ME Markov model,the new chunking model achieves better performance.
基金National Natural Science Foundation of China(41271556)National Natural Science Foundation of China and Russian Foundation for Basic Research(414110106515-56-53037)
文摘Plans for the Silk Road Economic Belt （SREB） include construction of two axes, two belts and two radiated areas. As a significant national strategy for China, the emphasis is on the construction of roads and achieving economic agglomeration and radiation through the construction of traffic axes. Using published literature and data analyses, this paper studied current traffic patterns between China and other regions within the SREB from the perspective of rail, ocean and air transportation. With regard to existing problems and development prospects of these three types of transportation, we propose construction modes for the traffic economic belt across continental plates and that future construction within the SREB should consider key cities as joints and arterial traffic lines as development axes, promote connecting of joints by lines, advance deep construction through joints and axes, connect lines into net, and develop informationalized traffic economic belt on the basis of trans-regional cooperation.
