Knowledge base question and answer method, electronic equipment and readable storage medium

Abstract

The invention discloses a knowledge base question and answer method, electronic equipment and a readable storage medium. The method comprises the following steps: step 1, constructing a corpus for a specific field; 2, training an MA-B model to classify questions to be answered; step 3, extracting user questions with the same field identifiers as the to-be-answered questions, and calculating similarity scores of the to-be-answered questions and the user questions; 4, determining similar questions of the to-be-answered questions by using the similarity scores, and taking answers corresponding to the similar questions as candidate answers; step 5, calculating a correlation score between each candidate answer and the question to be answered, and determining a final answer based on the correlation score and the similarity score; the invention is small in calculation amount, and the obtained final answer is highly matched with the to-be-answered question.

Description

Technical field [0001] The present invention belongs to the field of information processing, in particular to a knowledge base quiz method, electronic device, and readable storage medium. Background technique [0002] The automatic question and answer mainly includes question and answer based on traditional search engine. Based on the community-based question and answer, the knowledge base implements the language description of the objective world from the string to structured, reflecting the knowledge map of the objective world, because of its More accurate answers, I have received extensive attention from researchers, and has become the most important way of current question and answer systems; at present, there are already large-scale knowledge bases for English and Chinese, such as Freebase, YAGO, DBPEDIA, Baidu knowledge and Sogou knows cube, the construction of the knowledge base depends on the extraction of the identification and relationship of the entity, the entity iden...

AI Technical Summary

Problems solved by technology

[0003] With the rapid development of deep learning technology, more and more researchers have begun to turn their attention to the use of deep neural networks for knowledge base question answering, which regards knowledge base question answering as a semantic matching process, and directly obtains the user's answer through inter-vector calculation. In order to obtain more complete semantics, researchers integrate more information into word vector training, optimize the semantic representation of word vectors, and use vector representations to represent the relationship between entities in the knowledge base, among which TransE, TransH, and TransR are representative and STransE, however, the existing knowledge base Q&A efficiency and accuracy are poor and cannot meet the actual needs of users

Images