Chinese-Vietnamese parallel sentence pair extraction method based on cross-language bilingual pre-training and Bi-LSTM
A parallel sentence pair, pre-training technology, applied in natural language translation, neural learning methods, natural language data processing, etc., can solve the problem of data scarcity, poor effect of Chinese-Vietnamese bilingual parallel sentence pair extraction, and poor Chinese-Vietnamese machine translation effect. And other issues
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0061] Embodiment 1: as Figure 1-2 As shown, based on the Chinese-Vietnamese parallel sentence pair extraction method based on cross-language bilingual pre-training and Bi-LSTM, the specific steps of the Chinese-Vietnamese parallel sentence pair extraction method based on cross-language bilingual pre-training and Bi-LSTM are as follows:
[0062] Step1. Build a corpus: build a Chinese-Vietnamese comparable corpus, crawl Chinese-Vietnamese monolinguals, and build a Chinese-Vietnamese seed dictionary;
[0063] Step2, Chinese-Vietnamese cross-language word vector pre-training: Chinese-Vietnamese bilingual word vector representation is performed, and the Chinese-Vietnamese seed dictionary is used to align words in the same semantic space for cross-language bilingual pre-training;
[0064] Step3, Bi-LSTM and CNN unified spatial encoding: Then input the Chinese and Vietnamese sentences obtained after pre-training into a twin neural network composed of Bi-LSTM and CNN, and extract th...
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