Answer sequence discovery and generation

Abstract

Aspects of the present disclosure are directed toward discovering and generating answer sequences. Aspects are directed toward parsing, by a natural language processing technique configured to analyze syntactic and semantic content, a corpus of data for a subject matter. Aspects are also directed toward detecting a first set of answers including a first answer corresponding to a first answer category and a second set of answers including a second answer corresponding to a second answer category. Both the first and the second answer categories may relate to the subject matter. Aspects are also directed toward identifying a first set of ordering data for the first set of answers and the second set of answers. Aspects are also directed toward determining a first answer sequence corresponding to an order of the first set of answers and the second set of answers.

What is claimed is: 
     
         1 . A computer system, comprising:
 at least one processor;   a memory coupled to the at least one processor;   an answer sequence management mechanism executed by one or more of the at least one processor, the answer sequence management mechanism including:   a parsing module to parse, using a natural language processing technique configured to analyze syntactic and semantic content, a corpus of data for a subject matter;   a detecting module to detect, based on and in response to parsing, a first set of answers including a first answer corresponding to a first answer category and a second set of answers including a second answer corresponding to a second answer category, wherein both the first and the second answer categories relate to the subject matter;   a first identifying module to identify, based on the syntactic and semantic content, a first set of ordering data for the first set of answers and the second set of answers; and   a determining module to determine, in response to identifying the first set of ordering data, a first answer sequence corresponding to an order of the first set of answers and the second set of answers.   
     
     
         2 . The system of  claim 1 , further comprising:
 a second identifying module to identify, in response to receiving a question from a user, a first topic of the question; and   a selecting module to select, based on the first topic of the question, the corpus of data for the subject matter, wherein the first topic is related to the subject matter.   
     
     
         3 . The system of  claim 1 , further comprising an establishing module to establish, based on the syntactic and semantic content, a first sentiment factor for the first answer sequence. 
     
     
         4 . A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a first computing device, causes the computing device to:
 parse, by a natural language processing technique configured to analyze syntactic and semantic content, a corpus of data for a subject matter;   detect, based on and in response to parsing, a first set of answers including a first answer corresponding to a first answer category and a second set of answers including a second answer corresponding to a second answer category, wherein both the first and the second answer categories relate to the subject matter;   identify, based on the syntactic and semantic content, a first set of ordering data for the first set of answers and the second set of answers; and   determine, in response to identifying the first set of ordering data, a first answer sequence corresponding to an order of the first set of answers and the second set of answers.   
     
     
         5 . The computer program product of  claim 4 , further comprising computer readable program code configured to:
 derive, from the first answer sequence, a first set of answer attributes for the first answer and a second set of answer attributes for the second answer;   define, using the first set of answer attributes and the second set of answer attributes, a first-second answer rule; and   generate, using the first-second answer rule, an answer sequence model for developing answer sequences using machine learning techniques.   
     
     
         6 . The computer program product of  claim 5 , further comprising computer readable program code configured to:
 derive, from a second answer sequence, a third set of answer attributes for a third answer and a fourth set of answer attributes for a fourth answer;   define, using the third set of answer attributes and the fourth set of answer attributes, a third-fourth answer rule; and   add, to the answer sequence model, the third-fourth answer rule.   
     
     
         7 . The computer program product of  claim 6 , further comprising computer readable program code configured to:
 extract, by comparing the first-second answer rule and the third-fourth answer rule, a relationship between the first answer and the third answer; and   generate, using the relationship between the first answer and the third answer, a third answer sequence.   
     
     
         8 . The computer program product of  claim 7 , further comprising computer readable program code configured to:
 identify, as the first set of answer attributes, a group of characteristics for the first set of answers that indicates a correspondence between the first answer and the second answer; and   establish, based on the correspondence between the first answer and the second answer, the first-second answer rule to manage the generation of the third answer sequence.   
     
     
         9 . The computer program product of  claim 8 , wherein:
 extracting the relationship between the first answer and the third answer includes determining, based on the first-second answer rule and the third-fourth answer rule, an order component and an influence component of the first answer with respect to the third answer; and   generating the third answer sequence includes combining, based on the order component and the influence component, the first answer and the third answer.