Knowledge base question-answering method fusing fact texts
A knowledge base and fact technology, applied in text database clustering/classification, neural learning methods, unstructured text data retrieval, etc. The effect of improving the semantic gap, improving effectiveness and robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0020] Embodiment 1: as Figure 1-Figure 3 As shown, the knowledge base question answering method of fusing factual texts, the specific steps of the method are as follows:
[0021] Step1. Subject entity recognition: identify the subject entities in the natural language questions input into the system through the subject entity recognition model;
[0022] The subject entity refers to the knowledge base entity mentioned in the natural language question Q. For example, in the question "Where is YaoMing's birthplace?", the entity corresponding to "Yao Ming" in the knowledge base is the subject entity of the question. In our approach, a bidirectional recurrent neural network (e.g., BiLSTM) based model is employed to perform the subject entity recognition task. model such as figure 2 As shown, given a natural language problem Q=w containing n words 1 ,w 2 ,...,w n , first map its n words into a word vector {x j}, where j=1,...,n; then use BiLSTM to learn forward hidden state ...
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