抗人血红蛋白金标试剂条(Strip of gold-labeledanti-human-hemoglobin,SGI-antiHb),由于其使用方便、出现结果快速、直观可辨等优点,日益受到法医,尤其是基层法医的普遍欢迎.但国外公司生产的SGl-antiHb,本是为临床医学检验大便潜血所...抗人血红蛋白金标试剂条(Strip of gold-labeledanti-human-hemoglobin,SGI-antiHb),由于其使用方便、出现结果快速、直观可辨等优点,日益受到法医,尤其是基层法医的普遍欢迎.但国外公司生产的SGl-antiHb,本是为临床医学检验大便潜血所用,是否合乎法医学检验的标准和要求,未经检测很难定论.展开更多
Due to the fact that semantic role labeling （SRL） is very necessary for deep natural language processing, a method based on conditional random fields （CRFs） is proposed for the SRL task. This method takes shallow ...Due to the fact that semantic role labeling （SRL） is very necessary for deep natural language processing, a method based on conditional random fields （CRFs） is proposed for the SRL task. This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates＇ semantic roles in a sentence. The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features： features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected. Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80. 43 % precision and 63. 55 % recall for semantic role labeling.展开更多
文摘抗人血红蛋白金标试剂条(Strip of gold-labeledanti-human-hemoglobin,SGI-antiHb),由于其使用方便、出现结果快速、直观可辨等优点,日益受到法医,尤其是基层法医的普遍欢迎.但国外公司生产的SGl-antiHb,本是为临床医学检验大便潜血所用,是否合乎法医学检验的标准和要求,未经检测很难定论.
基金The National Natural Science Foundation of China(No60663004)the PhD Programs Foundation of Ministry of Educa-tion of China (No20050007023)
文摘Due to the fact that semantic role labeling （SRL） is very necessary for deep natural language processing, a method based on conditional random fields （CRFs） is proposed for the SRL task. This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates＇ semantic roles in a sentence. The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features： features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected. Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80. 43 % precision and 63. 55 % recall for semantic role labeling.
