Answer generation method based on multi-layer Transformer aggregation encoder

Abstract

The invention discloses an answer generation method based on a multilayer Transformer aggregation encoder, and the method comprises the steps: receiving input information which comprises paragraph article information and question information; converting the input information through a character embedding layer and a word embedding layer to obtain corresponding character vectors and word vectors; splicing the character vector and the word vector to obtain a spliced word vector; performing addition splicing on the spliced word vector and the position coding vector to obtain an input sequence; inputting the input sequence into a multi-layer Transformer aggregation encoder to obtain higher-level semantic information; inputting higher-level semantic information into a context-question attentionlayer, and learning question and answer information; inputting a learning result into an encoding layer comprising three multi-layer Transformer aggregation encoders, and obtaining a starting position and an ending position through a softmax function; and taking the content determined by the starting position and the ending position as a target answer. By applying the embodiment of the invention,the problems of information loss and insufficient performance in the prior art are solved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an answer generation method based on a multi-layer Transformer aggregation encoder. Background technique [0002] Question answering system is currently a hot research topic in the field of natural language processing in academia, and it is also one of the most widely used artificial intelligence applications in the industry. With the progress of the times and the rise of the era of Internet big data, people need to search for more and more information and knowledge information. In the context of big data, it is more and more difficult for people to obtain accurate result information only through search engines. Therefore, it is an urgent need to study some methods for answer generation in question answering systems. [0003] The question answering system is a system model for knowledge classification that organizes unordered corpus information in an orderly ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for generating answers based on a multi-layer Transformer aggregation encoder, aiming to solve the problems of existing information loss and insufficient performance

Images