Question-answering learning method and question-answering learning system using the same and computer program product thereof

A question-answering learning system, comprising:

• a classifier generation module configured to create a classifier module according to N1 labeled sentences among N sentences, wherein the classifier module includes a plurality of classifiers each representing different question-answering models, and both of the N and the N1 are positive integers, and each of the classifiers is configured to determine at least one corresponding sentence type of each of N2 unlabeled sentences among the N sentences, wherein the N2 is a positive integer;
• a consistency evaluation module is configured to:
• select, in a consistency evaluation process, N3 sentences from the N2 unlabeled sentences according to a degree of consistency of determined results of the classifiers, wherein the determined results of the N3 sentences are determined by the classifiers and are inconsistent, and the N3 is a positive integer;
• a complementarity evaluation module is configured to:
• select, in a complementarity evaluation process, N4 mutually complementary sentences as to-be-labeled sentences from the N3 sentences, wherein the N4 is a positive integer;
• wherein the classifier generation module is further configured to:
• re-create, after the N4 selected to-be-labeled sentences are labeled, the classifiers of the classifier module according to the N1 labeled sentences and the N4 selected to-be-labeled sentences;
• and
• wherein the question-answering learning system further comprises:
• a classifier evaluation module configured to add at least one of classifiers created prior to the recreation to the classifier module to be members of the classifier module.

A computer program product installed in a question-answering learning system to execute a question-answering learning method, wherein the question-answering learning method comprises:

• creating a classifier module by a classifier generation module according to N1 labeled sentences among N sentences, wherein the classifier module comprises a plurality of classifiers each representing different question-answering models, and both N and N1 are positive integers;
• determining at least one corresponding sentence type of each of N2 unlabeled sentences among the N sentences by each of the classifiers, wherein N2 is a positive integer;
• selecting, in a consistency evaluation process, N3 sentences from the N2 unlabeled sentences by a consistency evaluation module according to a degree of consistency of determined results of the classifiers, wherein the determined results of the N3 sentences are determined by the classifiers and are inconsistent, and N3 is a positive integer;
• selecting, in a complementarity evaluation process, N4 mutually complementary sentences as to-be-labeled sentences from the N3 sentences by a complementarity evaluation module, wherein N4 is a positive integer;
• re-creating, after the selected sentences are labeled, the classifiers of the classifier module by the classifier generation module according to the N1 labeled sentences and the selected sentences;
• and
• adding at least one of classifiers created prior to the recreation to the classifier module to be members of the classifier module by a classifier evaluation module.