A semantic similarity matching method and device based on a cross attention mechanism

Abstract

The invention provides a semantic similarity matching method and device based on a cross attention mechanism, computer equipment and a storage medium, is suitable for the technical field of voice interaction, and can realize cross representation of two statements on a semantic level. According to the method, firstly, word vector representation is carried out on each segmented word in two sentencesthrough word2vec, two splicing matrixes are obtained after bidirectional LSTM, then cross representation is carried out between the two splicing matrixes, and the importance degree of each segmentedword in any sentence relative to the other sentence is obtained. And on the basis, maximization processing is carried out and a full connection layer is input, and finally a matching degree score between the two statements is obtained. According to the scheme provided by the invention, the limitation existing when the LSTM is independently used or interactive matching is carried out in the prior art is overcome, so that the calculation of the matching degree between the two statements is more accurate and complete and approaches the real situation.

Description

technical field [0001] The invention relates to the technical field of voice interaction, in particular to a semantic similarity matching method, device, computer equipment and storage medium based on a cross-attention mechanism. Background technique [0002] The currently recognized semantic similarity matching methods based on deep learning include: 1) Siamese structure, that is, first two sentences or texts are represented by convolutional neural network (CNN), LSTM and other neural networks to obtain two sentence vectors, and then Carry out similarity calculation; 2) The method of interactive matching, that is, first perform an inner product operation between the word vectors of two sentences to obtain a three-dimensional matrix, and then input it into neural networks such as CNN and LSTM. However, the Siamese structure only independently represents the two sentences, and fails to accurately represent the interaction between the two sentences. On the other hand, the int...

AI Technical Summary

Problems solved by technology

However, the Siamese structure only independently represents the two sentences, and fails to accurately represent the interaction between the two sentences.

On the other hand, the interactive matching method only considers the point-to-point inner product operation, which can only express the local correlation between two sentences, and cannot effectively represent the semantic relationship

Images