Method and Apparatus for Extracting Entity Names and Their Relations

Abstract

According to one embodiment of the invention, a method includes generating a person-name Information Gain (IG)-Tree and a relation IG-Tree from annotated data. The method also includes tagging and partial parsing of an input document. The names of the persons are extracted within the input document using the person-name IG-tree. Additionally, names of organizations are extracted within the input document. The method also includes extracting entity names that are not names of persons and organizations within the input document. Further, the relations between the identified entity names are extracted using the relation-IG-tree.

1 - 30 . (canceled) 
     
     
         31 . A method comprising:
 generating a number of Information-Gain (IG)-Trees based on a memory learning technique and the extracted training sets; and   extracting entity names and relations between entity names based on the IG-Trees.   
     
     
         32 . The method of  claim 31 , further comprising:
 receiving annotated data;   parsing, at least partially, the annotated data, wherein parsing includes identifying syntactic structure of sentences within the annotated data; and   extracting training sets from the parsed annotated data, wherein the training sets are based on features including one or more of local context features, global context features, surface linguistic features, and deep linguistic features.   
     
     
         33 . The method of  claim 31 , wherein the number of IG-Trees is generated based on raw data that has been annotated. 
     
     
         34 . The method of  claim 33 , wherein the number of IG-Trees is generated based on a number of features of the annotated data. 
     
     
         35 . The method of  claim 31 , wherein the number of IG-Trees is selected from a group consisting of a person-name IG-Tree, an entity-name IG-Tree, a noun phrase IG-Tree and a relation IG-Tree. 
     
     
         36 . A machine-readable medium comprising instructions which, when executed by a machine, cause the machine to perform operations comprising:
 generating a number of Information-Gain (IG)-Trees based on a memory-learning technique and the extracted training sets; and   extracting entity names and relations between entity names based on the IG-Trees.   
     
     
         37 . The machine-readable medium of  claim 36 , wherein the operations further comprise:
 receiving annotated data;   parsing, at least partially, the annotated data, wherein parsing includes identifying syntactic structure of sentences within the annotated data; and   extracting training sets from the parsed annotated data, wherein the training sets are based on features including one or more of local context features, global context features, surface linguistic features, and deep linguistic features.   
     
     
         38 . The machine-readable medium of  claim 36 , wherein the number of IG-Trees is generated based on raw data that has been annotated. 
     
     
         39 . The machine-readable medium of  claim 37 , wherein the number of IG-Trees is generated based on a number of features of the annotated data. 
     
     
         40 . The machine-readable medium of  claim 36 , wherein the number of IG-Trees is selected from a group consisting of a person-name IG-Tree, an entity-name IG-Tree, a noun phrase IG-Tree and a relation IG-Tree. 
     
     
         41 . A system having a memory to store instructions, and a processing device to execute the instructions, wherein the instructions cause the processing device perform operations comprising:
 generating a number of Information-Gain (IG)-Trees based on a memory-learning technique and the extracted training sets; and   extracting entity names and relations between entity names based on the IG-Trees.   
     
     
         42 . The system of  claim 41 , wherein the operations further comprise:
 receiving annotated data;   parsing, at least partially, the annotated data, wherein parsing includes identifying syntactic structure of sentences within the annotated data; and   extracting training sets from the parsed annotated data, wherein the training sets are based on features including one or more of local context features, global context features, surface linguistic features, and deep linguistic features.   
     
     
         43 . The system of  claim 41 , wherein the number of IG-Trees is generated based on raw data that has been annotated. 
     
     
         44 . The system of  claim 42 , wherein the number of IG-Trees is generated based on a number of features of the annotated data. 
     
     
         45 . The system of  claim 41 , wherein the number of IG-Trees is selected from a group consisting of a person-name IG-Tree, an entity-name IG-Tree, a noun phrase IG-Tree and a relation IG-Tree.