Text error correction method and device

Abstract

The invention provides a text error correction method and device. The text error correction method comprises the following steps: inputting a word vector array corresponding to a text to be correctedinto a preset encoding module, obtaining a first hidden state vector array, inputting the first hidden state vector array into a decoding module, and for each decoding position, determining a decodingvector according to a second hidden state vector corresponding to the decoding position, an attention vector and the first hidden state vector array; and according to the decoding vector of the decoding position, a global word list and a limited word list corresponding to the words of the decoding position, determining the decoding result of the decoding position, so as to determine the text after being corrected corresponding to the text. In the text error correction method, the first hidden state vector array is adopted when the decoding vector is determined, so that the word sequence of the text is considered, and the accuracy of the error correction result is ensured; and due to the adoption of the limited word list, the size of the understanding space is limited, and the complexity of the error correction model is reduced, and the convergence speed of the model is increased.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a text error correction method and device. Background technique [0002] The current end-to-end error correction model is the NMT error correction model based on the introduction of attention mechanism. The NMT error correction model is a Sequence-To-Sequence model based on Encoder-Decoder. Among them, the structure of the Encoder module and the Decoder module is a recurrent neural network (Recurrent Neural Network, RNN for short) network structure, and the vocabulary used by the two to map the words / segments in the text sequence to the word vector space is the same. However, since the magnitude of the vocabulary is usually tens of thousands to hundreds of thousands, the solution space of the error correction model is too large when decoding the output, the complexity of the model is high, and the convergence speed of the model training is too slow. Moreover, ...

AI Technical Summary

Problems solved by technology

However, since the magnitude of the vocabulary is usually tens of thousands to hundreds of thousands, the solution space of the error correction model is too large when decoding the output, the complexity of the model is high, and the convergence speed of the model training is too slow.

And the attention mechanism does not consider the order of the original input sequence of the Encoder module, resulting in poor accuracy of error correction results

Images