Research Of Entity Knowledge Base System Based On Information Extraction

In recent years,the rapid development of the Internet and the high-speed increase in the amount of network data make it difficult for the traditional method to effectively obtain the useful information from the massive network data.the presentation of the information extraction and the entity knowledge base can solve this problem effectively.This thesis constructs the entity knowledge base system based on the named entity identification and the entity relation extraction from the information extraction.The work of the dissertation is partly supported by the National Natural Science Foundation of China(No.61271308,61172072,61401015)and Academic Discipline and Postgraduate Education Project of Beijing Municipal Commission of Education.In Chinese named entity recognition,the boundaries of words are difficult to identify and there are many kinds of naming rules for entities.This makes it more difficult to identify entities when dealing with English.In order to solve this problem,we use different methods to identify entities considering the types of named entities.The same type of entity usually has the same characteristics.By setting different feature templates,we can use conditional random field model to get entity identify templates.We also use the rules to calibrate the results of entity recognition.By doing so,the name entity recognition model can be created.This thesis presents an unsupervised entity relation extraction model,which can overcome the shortcomings of traditional methods,such as needing a lot of man-made work and poor portability.In this model,we create a filter function at first.Then we extract the relational feature words by using context window and parsing.We use affinity propagation clustering algorithm to get the relation of entities,which is much better than k-means clustering algorithm.In order to verify the effect of the method,this thesis carrys out the experiments by useing network data.By analyzing the experimental results,we can get that named entities and their relation can be effectively identified in entity knowledge base system.