Address Parsing System Based-On Google Map

With the development of GPS, Location-Based Service has been developed widely and applied in many fields such as location query service、point of interest search service、self-funded travel service and so on. To get the information of query address precisely, it is necessary to design a good location similarity match algorithm, which is not only one of the key techniques in the field of LBS, but also a very important research topic in the field of NLP. In this study, sentence similarity is introduced to solve this problem, it is an important research topic in the field of NLP and it has been applied in many fields such as text classification, machine translation and so on.In recent years, a great many methods have been proposed to measure the similarity of sentences, but these methods for computing sentence similarity have almost derived from approaches used for long text documents, they are not suitable for some applications.So this paper mainly focuses on very short sentence similarity computation, especially the similarity between Chinese and English addresses. In this paper, a new method has been devised to calculate the similarity between two addresses described by natural language. In the process of computation, the algorithm exploits the information of both structure and semantic information which include dictionary translation, word order analysis and so on. Meanwhile, it assigns a suitable weight value for each item in the word vector. Experimental result shows that the algorithm has high accuracy, the address in English to meet the application requirements of similarity calculation.A prototype system which use natural language as interface has been implemented based the algorithm in this study.