Transfer learning-based Chinese-Vietnamese neural machine translation method
A technology of machine translation and transfer learning, applied in the field of natural language processing, which can solve the problems of poor Chinese-Vietnamese neural machine translation, achieve good decoding effect and improve performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Embodiment 1: as Figure 1-2 As shown, the method of Chinese-Vietnamese neural machine translation based on transfer learning, the specific steps of the method are as follows:
[0031] Step1. Use crawlers to crawl the training corpus. The crawled training corpus includes Chinese-Vietnamese corpus with a scale of 100,000 sentence pairs; English-Vietnamese corpus with a scale of 700,000 sentence pairs; Chinese-English data with a scale of 50 million sentence pairs; Manually screen and then filter garbled characters; and extract a part from the training data as the test set and verification set;
[0032] The crawled corpus is manually screened and then word-segmented, Arabic numerals are replaced with "num" and garbled characters are filtered.
[0033] Step2. In the existing Chinese-English and English-Vietnamese data sets, use the back-translation method for the axis language English. First, use a 4-layer neural machine translation system based on the attention mechanism...
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