Method and system for extracting information from unstructured text using symbolic machine learning
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0044] Referring now to the drawings, and more particularly to FIGS. 1-12, exemplary embodiments of the present invention will now be described.
[0045] Machine learning approaches have the advantage that they require only labeled examples of the information sought. Much recent work on relational learning has been statistical. One such approach that reflects the state of the art for statistical methods is “Kernel Methods for Relation Extraction” by D. Zelenko, C. Aone, and A. Richardella, where the learning is of a function measuring similarity between shallow parses of examples. Statistical methods, in particular, need to have a large amount of labeled training data before anything useful can be done. This is a major problem for statistical approaches.
[0046] Work in another vein has concerned various attempts to accomplish relational learning by using heuristics to learn finite state recognizers or regular expressions, as exemplified by “Learning Information Extraction Rules for Se...
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