Generation apparatus, generation method, and program

Abstract

Aspects of the present invention disclose a method, computer program product, and system for generating target text based on target data. The method includes one or more processors decomposing one or more portions of text into at least one corresponding keyword and at least one corresponding template. The method further includes learning a classification model associated with selecting a template based on a category of a keyword. The method further includes identifying a target keyword that is represented by target data. The method further includes selecting a target template that is used to represent the target data based on a category associated with the identified target keyword utilizing the classification model. The method further includes generating target text that represents the target data based on the selected text template based on the selected target template and the identified target keyword.

What is claimed is: 
     
         1 . A computer-implemented method for generating target text based on target data, the method comprising:
 decomposing one or more portions of text into at least one corresponding keyword and at least one corresponding template;   learning a classification model associated with selecting a template based on a category of a keyword;   identifying a target keyword that is represented by target data;   selecting a target template that is used to represent the target data based on a category associated with the identified target keyword utilizing the classification model; and   generating target text that represents the target data based on the selected text template and the identified target keyword.   
     
     
         2 . The method of  claim 1 , further comprising:
 acquiring a target statistic as a statistic of an events that corresponds to the identified target keyword; and   selecting the target template based on the category associated with the identified target keyword and the target statistic, wherein learning the classification model is based on the category of the keyword and a statistic of an event that corresponds to the keyword.   
     
     
         3 . The method of  claim 2 , wherein the acquired target statistic is indicative of at least one of: a number of co-occurrences of a target keyword in a set of target keywords, a correlation between keywords in a set of target keywords, an increase in an event corresponding to the target keyword, and a decrease in an event corresponding to the target keyword. 
     
     
         4 . The method of  claim 1 , further comprising:
 storing keywords that belong to one or more categories respectively associated with the one or more categories; and   storing templates from the decomposed one or more portions of text, wherein the decomposing the one or more portions of text includes detecting a stored keyword from the one or more portions of text to determine a template based on areas of the one or more portions of text, not including the keyword in the one or more portions of text.   
     
     
         5 . The method of  claim 4 , further comprising correcting orthogonal variants of a keyword and a template from a decomposed portion of text based on one of: a stored keyword and a stored template. 
     
     
         6 . The method of  claim 5 , further comprising, in response to determining that an edit distance between a keyword obtained by decomposing a portion of text and a stored keyword is less than a predetermined reference distance, determining that the keyword obtained by decomposing a portion of text and the stored keyword are identical. 
     
     
         7 . The method of  claim 5 , further comprising, in response to determining that an edit distance between a template obtained by decomposing a portion of text and a stored template is less than a predetermined reference distance, determining that the template obtained by decomposing a portion of text and the stored template are identical. 
     
     
         8 . The method of  claim 4 , further comprising:
 providing an input section allowing for user input to enter target text and modify target text, wherein the provided input section includes, while a user in entering text, an input candidate and one or more of: a stored keyword and a stored template.   
     
     
         9 . A computer program product for generating target text based on target data, the computer program product comprising:
 one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions executable by one or more processors to cause the one or more processors to perform a method comprising:   decomposing one or more portions of text into at least one corresponding keyword and at least one corresponding template;   learning a classification model associated with selecting a template based on a category of a keyword;   identifying a target keyword that is represented by target data;   selecting a target template that is used to represent the target data based on a category associated with the identified target keyword utilizing the classification model; and   generating target text that represents the target data based on the selected text template and the identified target keyword.   
     
     
         10 . The computer program product of  claim 9 , wherein the method further comprises:
 acquiring a target statistic as a statistic of an events that corresponds to the identified target keyword; and   selecting the target template based on the category associated with the identified target keyword and the target statistic, wherein learning the classification model is based on the category of the keyword and a statistic of an event that corresponds to the keyword.   
     
     
         11 . The computer program product of  claim 10 , wherein the acquired target statistic is indicative of at least one of: a number of co-occurrences of a target keyword in a set of target keywords, a correlation between keywords in a set of target keywords, an increase in an event corresponding to the target keyword, and a decrease in an event corresponding to the target keyword. 
     
     
         12 . The computer program product of  claim 9 , wherein the method further comprises:
 storing keywords that belong to one or more categories respectively associated with the one or more categories; and   storing templates from the decomposed one or more portions of text, wherein the decomposing the one or more portions of text includes detecting a stored keyword from the one or more portions of text to determine a template based on areas of the one or more portions of text, not including the keyword in the one or more portions of text.   
     
     
         13 . The computer program product of  claim 12 , wherein the method further comprises:
 correcting orthogonal variants of a keyword and a template from a decomposed portion of text based on one of: a stored keyword and a stored template.   
     
     
         14 . The computer program product of  claim 13 , wherein the method further comprises:
 in response to determining that an edit distance between a keyword obtained by decomposing a portion of text and a stored keyword is less than a predetermined reference distance, determining that the keyword obtained by decomposing a portion of text and the stored keyword are identical.   
     
     
         15 . The computer program product of  claim 13 , wherein the method further comprises:
 in response to determining that an edit distance between a template obtained by decomposing a portion of text and a stored template is less than a predetermined reference distance, determining that the template obtained by decomposing a portion of text and the stored template are identical.   
     
     
         16 . The computer program product of  claim 12 , wherein the method further comprises:
 providing an input section allowing for user input to enter target text and modify target text, wherein the provided input section includes, while a user in entering text, an input candidate and one or more of: a stored keyword and a stored template.   
     
     
         17 . A computer system for generating target text based on target data, the computer system comprising:
 one or more computer processors;   one or more computer readable storage media; and   program instructions stored on the computer readable storage media for execution by at least one of the one or more processors to perform a method comprising:   decomposing one or more portions of text into at least one corresponding keyword and at least one corresponding template;   learning a classification model associated with selecting a template based on a category of a keyword;   identifying a target keyword that is represented by target data;   selecting a target template that is used to represent the target data based on a category associated with the identified target keyword utilizing the classification model; and   generating target text that represents the target data based on the selected text template based on the selected target template and the identified target keyword.   
     
     
         18 . The computer system of  claim 17 , wherein the method further comprises:
 acquiring a target statistic as a statistic of an events that corresponds to the identified target keyword; and   selecting the target template based on the category associated with the identified target keyword and the target statistic, wherein learning the classification model is based on the category of the keyword and a statistic of an event that corresponds to the keyword.   
     
     
         19 . The computer system of  claim 18 , wherein the acquired target statistic is indicative of at least one of: a number of co-occurrences of a target keyword in a set of target keywords, a correlation between keywords in a set of target keywords, an increase in an event corresponding to the target keyword, and a decrease in an event corresponding to the target keyword. 
     
     
         20 . The computer system of  claim 17 , wherein the method further comprises:
 storing keywords that belong to one or more categories respectively associated with the one or more categories; and   storing templates from the decomposed one or more portions of text, wherein the decomposing the one or more portions of text includes detecting a stored keyword from the one or more portions of text to determine a template based on areas of the one or more portions of text, not including the keyword in the one or more portions of text.