Information Extraction Module
The Information Extraction Module provides advanced text processing capabilities and information extraction from natural language input text.
Features Provided
- Text Categorization
- Allows you to assign custom categories to unstructured text. This is possible after you have trained a text categorization model using the Administration Utility. This feature can be used to index patient health-care reports, classify documents by domains and subdomains, and categorize email into SPAM and non-SPAM, among other applications.
- Entity Extraction
- Allows you to train models to extract entities from unstructured data. The Module ships
with some preexisting entities.
If required, define custom entities using the CustomEntity model type. After you create and train domain-specific models, you can extract entities based on the model trained by you.
- Relationship Extraction
- Allows you to identify the relationship type binding a pair of entities in any natural language input text.