Method and device for extracting English-Myanmar bilingual parallel sentence pairs based on bilstm-cnn
A parallel sentence pair and bilingual technology, applied in neural learning methods, semantic analysis, natural language data processing, etc., can solve problems such as missing, difficult to learn sentence representation, and unavoidable syntactic structure information, so as to improve accuracy and accuracy Enhanced effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] Embodiment 1: as Figure 1-7 As shown, the BiLSTM-CNN-based English-Myanmar bilingual parallel sentence pair extraction method, Figure 7 It is a flowchart of the present invention. The method includes the following steps: Step A: pre-training the English-Myanmar cross-language shared word embedding space, so that the words in different languages with similar semantics are close in the word vector space, and the semantic vector of the sentence representation is in the cross-English - Burmese semantic space has relevance; Step B: Functionally mark the sentence, splicing the syntactic structure information of each word into the word vector, and can obtain the syntactic difference between English and Burmese; Step C: Use BiLSTM to analyze the sentence in the sentence Forward and reverse information transmission of each word information, to obtain the feature state generated by different time series containing context information, and then use the characteristics of CNN ...
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