Text error correction model training and text error correction method and device

Abstract

The invention provides a text error correction model training and text error correction method and device, and relates to the technical field of natural language processing and deep learning. The text error correction model training method comprises the steps of obtaining training data; constructing a neural network model comprising a memory bank gating layer, a coding layer and an output layer, the memory bank gating layer being used for selecting a semantic unit from the historical text, and adding a coding vector of the selected semantic unit into a memory bank to perform error correction on the sample text; and training the neural network model by using the plurality of sample texts, the historical texts of the plurality of sample texts and the text labeling results of the plurality of sample texts until the neural network model converges to obtain a text error correction model. The text error correction method comprises the steps of obtaining a to-be-processed text and a historical text of the to-be-processed text; and taking the to-be-processed text and the historical text as input of the text error correction model, and taking an output result of the text error correction model as a text error correction result of the to-be-processed text.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, in particular to the technical fields of natural language processing and deep learning. Provided are a text error correction model training and text error correction method, device, electronic equipment and readable storage medium. Background technique [0002] Text error correction is a basic problem in Natural Language Processing (NLP), which can usually be preceded by other NLP tasks such as text retrieval, text classification, machine translation or sequence labeling to improve the validity of the input text and prevent The adverse effects of spelling mistakes. In the prior art, the text error correction is usually performed only according to the text to be corrected. Since the information contained in the text to be corrected is limited, the accuracy of the error correction result is low. Contents of the invention [0003] According to the first aspect of the present dis...

AI Technical Summary

Problems solved by technology

The existing technology usually only performs text error correction based on the text to be corrected itself, because the information contained in the text to be corrected is limited, so the accuracy of the error correction result is low

Images