A transformer-based Chinese blind translation method and system
A translation model and Chinese technology, applied in the field of automatic translation, can solve the problems of high cost, low translation efficiency and long construction time.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0076] like figure 1 and figure 2 As shown, this embodiment discloses a Transformer-based Chinese-Blind translation method, and the whole and / or partial contents of the preferred implementations of other embodiments can be used as supplements to this embodiment without causing conflicts or contradictions.
[0077] like figure 1 As shown, the Chinese-Blind translation method disclosed in this embodiment comprises the following steps:
[0078] S100: Train the translation model 20 based on the Chinese-blind digital resource 10 corresponding to the existing sentence level. Preferably, the Chinese Braille digital resource 10 may be an existing digital resource converted from Chinese to Braille. The Chinese-Blind digital resource 10 includes at least Chinese corpus and Braille corpus. Chinese corpus and Braille corpus store the same content. Each of the Braille corpus represents the second sentence of Braille, and there is a clear corresponding representation of the first senten...
Embodiment 2
[0123] like image 3 As shown, this embodiment discloses a Transformer-based Chinese-Blind translation system. The whole and / or part of the contents of the preferred implementations of other embodiments may be used as supplements to the present embodiment without causing conflict or contradiction.
[0124] The present invention also provides a Transformer-based Chinese-Blind translation system, which at least includes a translation logic component 30 that provides users with translation from Chinese text to Braille. The translation logic component 30 is configured to invoke the trained translation model 20 for translation. The translation model 20 is configured to be constructed based on the way that the Transformer takes sentences as a unit and directly converts Chinese text into Braille ASCII codes. The translation model 20 learns the Chinese-Blind digital resource 10 based on the multi-head self-attention mechanism by at least associating input, output, and input-output i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


