Knowledge graph embedding-based interpretable multi-hop question and answer method and system
A knowledge graph and explanatory technology, applied in the field of natural language processing, can solve problems such as lack of reasonability, limitation of accuracy, and inability to know the specific path, so as to achieve the effect of improving the effect and accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0059] Such as figure 1 As shown, an interpretable multi-hop question answering method based on knowledge graph embedding includes the following steps:
[0060] Step 1: Input the question sentence, and convert the encoded sentence to the relational space of the knowledge graph.
[0061] details as follows:
[0062] Step 1.1: Through the embedding layer, convert the context sentence into its sequence of word vector representations.
[0063] Specifically, the question sentence is segmented first, and a vocabulary is constructed. Among them, the Chinese word segmentation tool Jieba word segmentation (https: / / github.com / fxsjy / jieba) can be used to segment Chinese words. Since English has natural spaces, word segmentation is not required. Finally, through the embedding layer mapping, the sentence is converted into a sequence of word vector representations.
[0064] Step 1.2: Use the encoder to encode the word vector sequence of the question sentence, and output the coded repre...
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