Answer selection method and system for non-fact questions and answers

Abstract

The invention discloses an answer selection method for non-fact questions and answers, and belongs to the technical field of intelligent retrieval. The method comprises the steps of processing a question sentence and a to-be-selected answer statement by adopting a convolutional neural network based on an attention mechanism to obtain a first semantic vector and a second semantic vector, wherein the first semantic vector represents a semantic vector of the question sentence, and the second semantic vector represents a semantic vector of the to-be-selected answer statement; and matching the first semantic vector with the second semantic vector, and returning the to-be-selected answer statement corresponding to the second semantic vector with the highest matching degree as a correct answer. According to the method, the semantic vector representation of the sentence is generated by utilizing the convolutional neural network based on the attention mechanism, and a weight is given to an input by an importance degree in the semantic representation process, so that the influence of contents irrelevant to an answer theme is reduced, the high-quality semantic representation is automaticallygenerated, the semantic matching degree between the question sentence and the answer statement is improved, and the correct rate of answer selection is improved.

Description

technical field [0001] The invention relates to the technical field of intelligent retrieval, in particular to a method and system for selecting answers to non-factual questions and answers. Background technique [0002] The process of answering questions by non-factual question answering system is: question analysis, question retrieval and answer selection. First, determine the type of question and the type of expected answer through question analysis, and sometimes it is necessary to expand the keywords of the question; then use the type of question and keyword information to retrieve the set of candidate answers related to the question from the knowledge base; finally use Semantic feature matching selects the correct answer. The answer selection task is to find the semantic correlation between the question and the answer through semantic analysis, so as to select the correct answer. Non-factual Q&A in non-factual fields is characterized by the fact that the length of th...

AI Technical Summary

Problems solved by technology

[0006] The answer selection method based on deep learning also has corresponding disadvantages. For example, the semantic representation model based on neural network often processes the input text uniformly, and cannot recognize the noise information in the answer text, and a single network structure can only mine the same text. Semantic features, which make the final generated semantic vector can not express semantic information efficiently

In addition, the neural network training process has a large amount of calculations, and the model training time is relatively long. Ultimately, the network structure is difficult to explain, and the final results of the model can only be used to verify the performance of the network structure and its combination.

Images