Sentence similarity assessment method based on deep semantic model and semantic role labeling
A technology for semantic role labeling and sentence similarity, which is applied in semantic analysis, natural language data processing, special data processing applications, etc., and can solve problems such as insufficient use of verb component information.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The present invention will be further elaborated below in conjunction with the accompanying drawings of the description.
[0047] Such as figure 1 Therefore, a method for evaluating sentence similarity based on deep semantic model and semantic role labeling of the present invention comprises the following steps:
[0048] 1) Establish a deep semantic model: map a relatively short text string to a feature vector in a low semantic space, and after obtaining the semantic feature vector of each sentence, use cosine similarity to measure the semantic similarity between two sentences Spend;
[0049]2) Semantic role classification processing: A0, A1, A2 (A0, A1, A2 are public semantic role identifiers) existing semantic roles are reserved, and other semantic roles are uniformly processed as a class of semantic roles;
[0050] 3) Predicate similarity calculation: on the basis of semantic role classification, for multi-predicate sentences, sentence pairs are paired according to...
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