Entity Extraction Components
Spectrum Entity Extraction includes these stages.
- Read From Documents—Reads unstructured input data from various file formats and extracts the contents.
- Entity Extractor— Extracts entities such as names and addresses from unstructured data passed as strings.
- Text Categorizer— Assigns custom categories to unstructured content or plain text (such as email, news articles, and comments) based on how much of that content contains material for that category.
- Relationship Extractor— Extracts relationships between entities.