基于多算法融合的化工突发事件信息抽取研究

摘要

The chemical emergency information management is based on the requirements for the extraction of the effective chemical emergencies of certain information and the application in chemical emergency management.the method of multi algorithm fusion is put forward based on rule model and machine learning are combined to extract chemical emergencies information.First in order to extract the relevant information of some chemical emergencies,to extract the information of different formulated a series of different extraction rules,and then through a series of feedback,by using machine learning algorithm is the keyword extraction algo-rithm and the dependency syntactic parsing algorithm to extract rules to add modify,thereby optimizing the chemical burst event ex-traction algorithm.Finally,a large number of experiments show that the method has high accuracy,and the results are ideal.%基于对化工突发事件信息管理的要求,为了有效地抽取化工突发事件的某些特定信息并应用于化工突发事件管理,提出了基于多算法融合的方法即规则模式及机器学习相结合的方法来抽取化工突发事件信息.首先为了抽取化工突发事件的某些相关信息,根据所抽取信息的不同制定了一系列不同的抽取规则,然后通过一系列的反馈,利用机器学习算法即关键字提取算法以及依存句法分析算法相融合的方法来进行抽取规则的添加修改,从而优化了化工突发事件抽取算法.最后通过大量有效性的实验表明,该信息抽取方法有较高的准确率,抽取的结果较为理想.