A Neural Network Mongolian-Chinese Machine Translation Method
A neural network and machine translation technology, applied in the field of neural network Mongolian-Chinese machine translation, can solve problems such as mistranslation and processing of unregistered words
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0064] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.
[0065] Description of the problem: The neural network-based Mongolian-Chinese translation system model includes the construction of a mixed encoder and decoder + a wrong-translation and omission-translation processing model.
[0066] Such as figure 1 Shown is the composition of the hybrid encoder, which consists of three types of encoders, including grapheme-level encoders, word-level encoders, and phrase encoders, which encode grapheme, word, and phrase as the basic units of a sentence. At the end of the encoder, the vector information corresponding to the three types of encoders is fused through a fusion function to form a hybrid encoder.
[0067] figure 2 It is the overall structure diagram of the machine translation system, which is composed of a hybrid encoder, attention mechanism and decoder. During training, the hybrid encoder encodes ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com