A Chinese-blind automatic conversion method and system based on depth neural network

Abstract

The invention relates to a Chinese-blind automatic conversion method and system based on depth neural network, includes obtaining Chinese-blind bilingual corpus for sentence and word level comparison,training depth neural network with Chinese-blind bilingual corpus to obtain word segmentation model for Chinese character string segmentation, and ussing Chinese-blind bilingual corpus to obtain tone-marking model for Chinese character tone marking; obtaining The Chinese character text to be converted, and segmenting the Chinese character text according to Braille rules using a word segmentationmodel to obtain a plurality of characters and words, and performing tone marking on the characters and words to be converted using a tone-marking model to convert the tone-marked characters and wordsinto Braille. The invention adopts the trained model to directly segment Chinese character strings according to Braille rules. Therefore, the Chinese character information can be fully utilized to avoid the problem that the Chinese character information is lost and the homophone words are confused with each other when the Braille string is segmented, and the segmentation effect is affected. By using the depth neural network model and the calibration model, higher conversion accuracy can be obtained.

Description

technical field [0001] The invention relates to the technical field of automatic conversion from Chinese to Braille, especially the field of using a deep neural network to convert Chinese to Braille. Background technique [0002] Braille is an important way for blind people to read and obtain information. It is a tactile symbology, printed on paper or displayed on a dot display, that is read by touch. The basic unit of Braille is called "square". One side contains 6 dots. By setting whether each dot is a dot or not, a total of 64 combinations can be formed. These combinations constitute the most basic Braille symbols. [0003] In order to generate Braille content, textual content used by ordinary people needs to be converted into Braille. For alphabetic scripts, there is a direct mapping from letters to Braille symbols, and the conversion is relatively simple. Currently, computerized systems are available for automatic conversion of English, Portuguese, Danish, Spanish, H...

AI Technical Summary

Problems solved by technology

However, this method also has shortcomings: on the one hand, this method is based on traditional machine learning methods such as perceptron models and statistical machine learning, and in recent years, deep learning technology has gradually replaced these traditional methods in many fields; more importantly, Yes, the model training of this method is based on Braille corpus, and Braille only represents the pronunciation of Chinese characters (and most of them do not add tones), which may cause ambiguity due to homonyms. For example, "form" and "situation" are exactly the same in Braille," "Time", "Event", and "Practice" also correspond to the same Braille in most cases, and a large number of single-character words have homophonic confusion, which will directly affect the final word segmentation results

In actual operation, the recognition of rare words, content words, and monosyllabic words that need to be marked is relatively subjective or involves understanding of grammar and semantics, and it is difficult for computers to process

Therefore, the current automatic Chinese-blind conversion method is generally based on rules, and only standardizes simple situations such as certain homophones and clearly defined monosyllabic words. The standardization rate is far lower than manual standardization, which is likely to cause difficulties for blind people

Images