Text error correction method based on XLNet-BiGRU
A text error correction, Chinese technology, applied in the field of XLNet-BiGRU text error correction, can solve the problems of inapplicability, time-consuming, etc., and achieve the effect of improving time-consuming
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2022-02-18
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the fields of artificial intelligence and natural language processing, in particular to an XLNet-BiGRU text error correction method. Background technique
[0002] Text error correction is a natural language processing technology that corrects erroneous content in text, specifically including spelling error correction, grammatical error correction, and semantic-pragmatic error correction in specific scenarios. Among them, spelling error correction is characterized by not changing the length of the text, but only one-to-one correction of typos in the text; grammatical error correction and semantic pragmatic error correction need to deal with multiple word errors, few word errors, and word usage in the text. Mistakes, such as mistakes and wrong word order, may change the length of the text.
[0003] In recent years, large-scale deep pre-trained language models such as BERT and XLNet have promoted the rapid development of the fiel...
Examples
Embodiment 1
[0049] Such as figure 1 Shown, a kind of text error correction method based on XLNet-BiGRU of the present invention comprises following steps:
[0050] S1. Training XLNet (Generalized Autoregressive Pretraining for Language Understanding) Chinese model based on large-scale unlabeled corpus.
[0051] The XLNet model mainly includes Permutation Language Model, Two-Stream Self-Attention and Transformer-XL core components.
[0052] Further, the permutation language model included in the XLNet model aims to randomly shuffle the Chinese characters in the sentences in the text. For the Chinese character x i , the Chinese {x that originally appeared behind it i+1 ,...,x n} can also appear in front of it, assuming that the text sequence of length T is [1,2,...,T] and all permutations are A T , a t is the tth element in the sequence, and aT The previous element of , this modeling process can be expressed as:
[0053]
[0054] where θ is the model parameter with training.
[00...