SAS Content Categorization Studio: Building Models

This course gives a practical introduction to methods of document classification and content identification using SAS Content Categorization Studio.

Aprenderá a

• describe the architecture and workflow for SAS Content Categorization
• define content categorization, concept extraction, and contextual extraction
• use automatic methods to categorize documents based on their topic
• write rules to categorize documents according to topic
• create rules to extract key pieces of information from documents.

Quién debe atender

Persons responsible for the development and/or testing of category rules and concept definitions; also beneficial for those who want to understand techniques for working with unstructured data

Formatos disponibles	Duración
Classroom:	2.0 días

No SAS or programming experience is required. You should be able to log on and off a computer, use a keyboard and mouse, and have a preliminary understanding of the differences between structured (numeric) and unstructured (text) data fields.

This course addresses SAS Enterprise Content Categorization, SAS Text Analytics Common Components software.

Introduction to SAS Content Categorization Studio

• architecture and workflow
• content categorization and concept extraction
• the SAS Content Categorization Studio Interface

Content Categorization

• introduction to content categorization
• automatic rule generation
• testing a categorizer
• determining category membership
• writing rules
• building a statistical categorizer (self-study)

Contextual Extraction

• introduction to contextual extraction
• determining concept matches
• CLASSIFIER and REGEX definitions
• CONCEPT and C_CONCEPT definitions
• CONCEPT_RULE, NO_BREAK, and REMOVE_ITEM definitions
• SEQUENCE and PREDICATE_RULE definitions

Concept Extraction (Self-Study)

• introduction to concept extraction
• determining concept matches
• writing classifier definitions
• writing grammar definitions