Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based o...Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based on machine learning requires a lot of hand-marked work, and exploring more features from discourse. A method of two-stage machine learning based on temporal relation computation （TSMLTRC） is proposed in this paper for the shortcomings of current temporal relation computation between two events. The first stage is to get the main temporal attributes of event based on classification learning. The second stage is to compute the event temporal relation in the discourse through employing the result of the first stage as the basic features, and also employing some new linguistic characteristics. Experiments show that, compared with the artificial golden rule, the computational efficiency in the first stage is much higher, and the F1-Score of event temporal relation which is computed through combining multi-features may be increased at 85.8% in the second stage.展开更多
时间关系的识别成为近年来自然语言处理领域(nature language processing,NLP)的一个研究热点。引入时间片段和主题片段这两种比事件触发词粒度粗的语义单元进行时间关系识别,首先在文本中利用一些时间篇章特点识别时间片段,然后利用相...时间关系的识别成为近年来自然语言处理领域(nature language processing,NLP)的一个研究热点。引入时间片段和主题片段这两种比事件触发词粒度粗的语义单元进行时间关系识别,首先在文本中利用一些时间篇章特点识别时间片段,然后利用相似度计算与支持向量机(support vector maehine,SVM)模型相结合的方法识别主题片段,最后在主题片段范围内,以时间片段为排序对象,使用最大熵分类模型识别时间关系。在TempEval-2010的汉语语料上进行实验,得到的时间关系识别宏平均精确率为60.09%。实验结果表明:引入时间片段后可有效减少不必要的事件时序关系的识别;同时,在主题片段的约束下所得到的时间关系更简洁、语义逻辑性更好。展开更多
Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information...Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.展开更多
In order to relate the design and analysis of an optical pattern recognition system with the structural parameters, only by introducing the prolate spheroidal wave function (PSWF) can the amount of information be comp...In order to relate the design and analysis of an optical pattern recognition system with the structural parameters, only by introducing the prolate spheroidal wave function (PSWF) can the amount of information be computed. Combining the imaging wave function set {ψi(x)} and distorted wave function set {b_i(p)} and two integral equations they satisfy derives the expression of the amount of information. The design method of matched filter connected with its amount of information is studied, and their amounts of information belonging to different pattern recognition systems are illustrated. It can be seen that the difference of the amounts of information for various systems is obvious.展开更多
基金Project supported the National Natural Science Foundation of China(Grant No.60975033)the Basic Scientific Research Project of International Centre for Bamboo Rattan(Grant No.1632009006)the Shanghai Leading Academic Discipline Project(Grant No.J50103)
文摘Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based on machine learning requires a lot of hand-marked work, and exploring more features from discourse. A method of two-stage machine learning based on temporal relation computation （TSMLTRC） is proposed in this paper for the shortcomings of current temporal relation computation between two events. The first stage is to get the main temporal attributes of event based on classification learning. The second stage is to compute the event temporal relation in the discourse through employing the result of the first stage as the basic features, and also employing some new linguistic characteristics. Experiments show that, compared with the artificial golden rule, the computational efficiency in the first stage is much higher, and the F1-Score of event temporal relation which is computed through combining multi-features may be increased at 85.8% in the second stage.
文摘时间关系的识别成为近年来自然语言处理领域(nature language processing,NLP)的一个研究热点。引入时间片段和主题片段这两种比事件触发词粒度粗的语义单元进行时间关系识别,首先在文本中利用一些时间篇章特点识别时间片段,然后利用相似度计算与支持向量机(support vector maehine,SVM)模型相结合的方法识别主题片段,最后在主题片段范围内,以时间片段为排序对象,使用最大熵分类模型识别时间关系。在TempEval-2010的汉语语料上进行实验,得到的时间关系识别宏平均精确率为60.09%。实验结果表明:引入时间片段后可有效减少不必要的事件时序关系的识别;同时,在主题片段的约束下所得到的时间关系更简洁、语义逻辑性更好。
文摘Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.
基金Project supported by the National Natural Science Foundation of China.
文摘In order to relate the design and analysis of an optical pattern recognition system with the structural parameters, only by introducing the prolate spheroidal wave function (PSWF) can the amount of information be computed. Combining the imaging wave function set {ψi(x)} and distorted wave function set {b_i(p)} and two integral equations they satisfy derives the expression of the amount of information. The design method of matched filter connected with its amount of information is studied, and their amounts of information belonging to different pattern recognition systems are illustrated. It can be seen that the difference of the amounts of information for various systems is obvious.
