1.1 - 8.10 - NER Functions (Maximum Entropy Model Implementation) - Teradata Vantage

Teradata Vantage™ - Machine Learning Engine Analytic Function Reference

Teradata Vantage
Release Number
October 2019
Content Type
Programming Reference
Publication ID
English (United States)
Function Description
NamedEntityFinderTrainer (ML Engine) Takes training data and outputs a maximum entropy model (binary file).
NamedEntityFinder (ML Engine) Evaluates input, identifies tokens based on specified model, and outputs tokens with detailed information.

Uses model to extract entity types 'PERSON', 'LOCATION', and 'ORGANIZATION' and rules to extract entity types 'DATE', 'TIME', 'EMAIL' and 'MONEY'. If you specify these entity names, the function invokes the default model types and model file names. To extract all entities in one NamedEntityFinder call, specify 'ALL'.

Named Entity Finder Evaluator (ML Engine) Evaluates maximum entropy model.

The maximum entropy model implementation supports only English text.