Reading understanding method and system based on collaborative attention and self-adaptive adjustment

Abstract

The invention discloses a reading understanding method and system based on collaborative attention and self-adaptive adjustment, which belong to the technical field of machine reading understanding. The method is characterized by comprising the following steps: S1, inputting a document word vector and a problem word vector, and training the document word vector and the problem word vector, the word vector comprising two granularities of character-level embedding and word embedding; s2, calculating a similarity weight of the problem and the document by using cosine similarity, and performing adaptive adjustment on document word embedding according to the similarity weight; s3, encoding the document word vector and the problem word vector through a multi-layer bidirectional gating loop unit;s4, using a collaborative attention mechanism for the document and the question, and obtaining a document vector representation query-aware with question perception and a question vector representation para-aware with document perception; s5, learning an internal dependency relationship between the document and the question by using a self-attention mechanism, and obtaining a new semantic vectorrepresentation; s6, using the attention as a pointer, predicting the starting position and the ending position of the answer, and extracting an answer sequence according to the answer span.

Description

technical field [0001] The invention belongs to the technical field of machine reading comprehension, and in particular relates to a reading comprehension method and system based on cooperative attention and self-adaptive adjustment. Background technique [0002] In natural language processing and artificial intelligence research, machine reading comprehension focuses on the ability to understand and reason about natural language, which is a challenging task. Machine reading comprehension means that documents and questions are given in the form of natural language, and the machine returns the correct answer through understanding and reasoning of natural language. According to the type of question, reading comprehension tasks can be divided into three categories: answer-choice type, cloze type and question-answer type. The answer selection type aims to select the option closest to the semantics of the document as the correct answer from multiple candidate answers based on th...

AI Technical Summary

Problems solved by technology

However, the problem of information loss caused by the aggregation of long text sequences using cyclic neural networks is often ignored, which affects the performance of the model

Images