Machine learning of colloquial place names

Abstract

Provided are systems and methods directed to identifying relationships between colloquial place names in a relational database. In some embodiments, a method of identifying relationships between colloquial place names in a relational database comprises receiving geographic location information; generating a vector corresponding to the geographic location; comparing the geographic location information vector to a plurality of colloquial place name vectors in a relational database that maps a plurality of colloquial place names to a plurality of corresponding colloquial place name vectors in a vector space, to generate a plurality of similarity scores that is calculated based on the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vectors; and identifying that one or more colloquial place names in the relational database are related to the geographic location information based on the plurality of similarity scores.

1 . A method of identifying relationships between colloquial place names in a relational database comprising:
 receiving geographic location information;   generating a geographic location information vector corresponding to the geographic location;   comparing the geographic location information vector corresponding to the geographic location to a plurality of colloquial place name vectors in a relational database that maps a plurality of colloquial place names to a plurality of corresponding colloquial place name vectors in a vector space, wherein each colloquial place name vector represents one or more words associated with each colloquial place name, to generate a plurality of similarity scores that is calculated based on the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vectors; and   identifying that one or more colloquial place names in the relational database are related to the geographic location information based on the plurality of similarity scores.   
     
     
         2 . The method of  claim 1 , comprising outputting the one or more colloquial place names related to the geographic location information based on the similarity score onto a display. 
     
     
         3 . The method of  claim 1 , comprising storing the similarity score calculated based on the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vectors in the relational database. 
     
     
         4 . The method of  claim 1 , comprising updating the relational database based on the geographic location information and the similarity score between the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vector. 
     
     
         5 . The method of  claim 1 , wherein each colloquial place name vector of the plurality of colloquial place name vectors is generated by word-embedding one or more words associated with a colloquial place name of the plurality of colloquial place names, wherein a first colloquial place name vector represents a first colloquial place name and a second colloquial place name vector represents a second colloquial place name. 
     
     
         6 . The method of  claim 1 , wherein the similarity score is calculated between the geographic location information vector and each colloquial place name vector by calculating a cosine similarity between the geographic location information vector and each colloquial place name vector located in the vector space. 
     
     
         7 . The method of  claim 1  comprising:
 for each user account of a plurality of user accounts, receiving a plurality of colloquial place names associated with each user account; and 
 inputting the plurality of colloquial place names associated with each user account into a word-embedding algorithm to generate a mapping of the plurality of colloquial place names to the plurality of corresponding colloquial place name vectors, wherein the plurality of colloquial place name vectors corresponds to the plurality of colloquial place names. 
 
     
     
         8 . The method of  claim 7 , wherein the word-embedding algorithm comprises one of word2vec, GloVe, or FastText. 
     
     
         9 . A system for identifying relationships between colloquial place names in a relational database comprising:
 one or more processors and memory storing one or more programs that when executed by the one or more processors cause the one or more processors to:   receive geographic location information;   generate, based on the geographic location information, a vector corresponding to the geographic location;   compare the geographic location information vector corresponding to the geographic location to a plurality of colloquial place name vectors in a relational database that maps a plurality of colloquial place names to a plurality of corresponding colloquial place name vectors in a vector space, wherein each colloquial place name vector represents one or more words associated with each colloquial place name, to generate a plurality of similarity scores that is calculated based on the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vectors; and   identify that one or more colloquial place names in the relational database are related to the geographic location information based on the plurality of similarity scores.   
     
     
         10 . The system of  claim 9 , comprising output the one or more colloquial place names related to the geographic location information based on the similarity score onto a display. 
     
     
         11 . The system of  claim 9 , comprising store the similarity score calculated based on the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vectors in the relational database. 
     
     
         12 . The system of  claim 9 , comprising update the relational database based on the geographic location information and the similarity score between the geographic location information vector and each colloquial place name vector of the plurality of colloquial place name vector. 
     
     
         13 . The system of  claim 9 , wherein each colloquial place name vector of the plurality of colloquial place name vectors is generated by word-embedding one or more words associated with a colloquial place name of the plurality of colloquial place names, wherein a first colloquial place name vector represents a first colloquial place name and a second colloquial place name vector represents a second colloquial place name. 
     
     
         14 . The system of  claim 9 , wherein the similarity score is calculated between the geographic location information vector and each colloquial place name vector by calculating a cosine similarity between the geographic location information vector and each colloquial place name vector located in the vector space. 
     
     
         15 . The system of  claim 9  comprising:
 for each user account of a plurality of user accounts, receive a plurality of colloquial place names associated with each user account; and 
 input the plurality of colloquial place names associated with each user account into a word-embedding algorithm to generate a mapping of the plurality of colloquial place names to the plurality of corresponding colloquial place name vectors, wherein the plurality of colloquial place name vectors corresponds to the plurality of colloquial place names. 
 
     
     
         16 . The system of  claim 15 , wherein the word-embedding algorithm comprises one of word2vec, GloVe, or FastText.