Mongolian-Chinese non-autoregressive machine translation method based on knowledge graph
A knowledge graph and machine translation technology, applied in the field of Mongolian-Chinese non-autoregressive machine translation based on knowledge graph, can solve problems such as the inability of the decoder to decode in parallel, the lack of target sequence dependencies, and the translation effect not reaching the ideal state of researchers.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0025] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.
[0026] First, the present invention is to come up with a pair of parallel sentences used in the corpus "Two villages across the river" as an example the following process.
[0027] like figure 1 , The present invention provides a non-Mongolian and Chinese-based mapping knowledge autoregressive machine translation method, comprising the steps of:
[0028] Step 1, Mongolian and Chinese bilingual named entity constructing semantic web by mapping knowledge triples, where the unknown word is a named entity represents a portion of the knowledge map triples. The present invention is directed to named entities alignment problems introduced triplet mapping knowledge build named entity named entity formed in the center of the Semantic Web context, use can be well aligned named entity context information.
[0029] On the basis of mutual information feat...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap