Text similarity calculation method of Siamese network based on ALBERT

Abstract

Text similarity calculation based on deep learning has always been an important research in the field of natural language processing. However, the traditional deep learning model has some disadvantages in the application of text similarity calculation, Text similarity calculation based on deep learning has always been an important research in the field of natural language processing. However, traditional deep learning models have drawbacks in the application of text similarity calculation, such as insufficient extraction of text semantics, inability to combine context, and inability to Understand polysemy and so on. In order to solve the problems of existing text similarity calculation methods based on deep learning, this paper proposes a Siamese network based on ALBERT, uses ALBERT model for word embedding, and proposed the ABSBGRU model by combining Bi-GRU of Siamese structure with attention mechanism. On the premise of minimizing the increased computational cost, we can extract the deep semantic information better. The experimental results show that ABSBGRU model has stronger deep semantic extraction ability. Compared with other traditional models, F1 Score is higher and training cost less than some other models.