Machine reading model training method and device, question and answer method and device

Abstract

The invention discloses a machine reading model training method and device, a question and answer method and a device, and belongs to the field of natural language processing. The machine reading model training method comprises the following steps: acquiring a training sample, wherein the training sample comprises a sample question and a corresponding sample article, a real initial position and areal final position of the corresponding answer in the sample article; extracting a question feature vector of the sample question and an article feature vector of the sample article, and using a neural network structure to fuse and process the question feature vector and the article feature vector to form a fusion result; inputting the fusion result into a classifier to perform prediction of theinitial position and the final position of the answer; performing error calculation on the predicted initial position and final position, and the real initial position and the real final position of the answer; and optimizing the neural network structure according to the error calculation result. According to the machine reading model training method and device, the question and answer method anddevice in the embodiment of the invention, the corresponding answer can be directly extracted from the entire associated article through end-to-end deep learning.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a machine reading model training method and device, and a question answering method and device. Background technique [0002] There are many ways to implement the technical architecture of the mainstream question answering system, such as: search engine based on pure keyword matching, method of extracting semantic similarity features based on natural language processing, and sequence-to-sequence (seq2seq) generation based on deep learning dialog method. [0003] However, there are many problems in the existing question answering systems, as follows: [0004] For the retrieval-based question answering system, its retrieval-based question-answering method cannot achieve true semantic matching to the questions entered by the user, and often the answer is not what is asked. Some of these special cases can be handled by manually adding rules, but this method has high maint...

AI Technical Summary

Problems solved by technology

This method is difficult to implement and requires a huge amount of corpus for training. At present, because of the low controllability of generative answers, it is rarely used in landing projects.

Images