Answer sequence evaluation

1. A computer implemented method for evaluating an answer sequence comprising:

receiving, by a question-answering system and via a graphical user interface, an input query from a user;

parsing, using natural language processing techniques configured to parse semantic and syntactic content and by the question-answering system, the input query;

searching, based on the parsed input query and by the question-answering system, a set of corpora;

generating, based on the searching and by the question-answering system, a set of answer sequences including a first answer sequence having a first set of answers and a set of scores coupled with the first set of answers;

identifying, by the question-answering system, a set of answer categories corresponding to the first set of answers of the first answer sequence;

collecting, by the question-answering system and for the set of answer categories corresponding to the first set of answers of the first answer sequence, context data from the set of corpora indicating a relative importance of a first answer category of the set of answer categories to the first answer sequence;

determining, by the question-answering system and based on a subject matter corresponding to the first answer sequence, a set of evaluation rules, wherein a first evaluation rule of the set of evaluation rules comprises:

assigning, based on the context data, a first weighting value to the first answer category of the set of answer categories;

assigning, based on the context data, a second weighting value to a second answer category of the set of answer categories; and

calculating, by a statistical algorithm using the first weighting value and the second weighting value, an aggregate score;

receiving, by the question-answering system and from the user, a first set of answer preference data indicating an inclination for the first answer category of the set of answer categories;

increasing, by the question-answering system and based on the first set of answer preference data, the first weighting value assigned to the first answer category;

generating, by the question-answering system and based on the set of scores and the set of evaluation rules, a first sequence evaluation score for the first answer sequence, wherein generating the first sequence evaluation score for the first answer sequence includes assigning, to the first answer sequence, the aggregate score as the first sequence evaluation score;

comparing, by the question-answering system, the first sequence evaluation score to sequence evaluation scores of other answer sequences of the set of answer sequences; and

providing, by the question-answering system and based on the comparing the sequence evaluation scores, the first answer sequence to the user, via the graphical user interface, as a response to the input query.

2. The method of claim 1 , further comprising:

receiving, from the user, a second set of answer preference data indicating a disinclination for the second answer category of the set of answer categories; and

decreasing, based on the second set of answer preference data, the second weighting value assigned to the second answer category.

3. A computer implemented method for evaluating an answer sequence comprising:

receiving, by a question-answering system and via a graphical user interface, an input query from a user;

parsing, using natural language processing techniques configured to parse semantic and syntactic content and by the question-answering system, the input query;

searching, based on the parsed input query and by the question-answering system, a set of corpora;

generating, based on the searching and by the question-answering system, a set of answer sequences including a first answer sequence having a first set of answers and a set of scores coupled with the first set of answers;

identifying, by the question-answering system, a set of answer categories corresponding to the first set of answers of the first answer sequence;

collecting, by the question-answering system and for the set of answer categories corresponding to the first set of answers of the first answer sequence, context data from the set of corpora indicating a relative importance of a first answer category of the set of answer categories to the first answer sequence;

determining, by the question-answering system and based on a subject matter corresponding to the first answer sequence, a set of evaluation rules, wherein a first evaluation rule of the set of evaluation rules comprises:

assigning, based on the context data, a first weighting value to the first answer category of the set of answer categories;

assigning, based on the context data, a second weighting value to a second answer category of the set of answer categories; and

calculating, by a statistical algorithm using the first weighting value and the second weighting value, an aggregate score;

receiving, by the question-answering system and from the user, a first set of answer preference data indicating a disinclination for the first answer category of the set of answer categories;

decreasing, by the question-answering system and based on the first set of answer preference data, the first weighting value assigned to the first answer category;

generating, by the question-answering system and based on the set of scores and the set of evaluation rules, a first sequence evaluation score for the first answer sequence, wherein generating the first sequence evaluation score for the first answer sequence includes assigning, to the first answer sequence, the aggregate score as the first sequence evaluation score;

comparing, by the question-answering system, the first sequence evaluation score to sequence evaluation scores of other answer sequences of the set of answer sequences; and

providing, by the question-answering system and based on the comparing the sequence evaluation scores, the first answer sequence to the user, via the graphical user interface, as a response to the input query.