Intellexer Categorizer – How Document Categorizer Works

Online Demo

Use Case:

"We discovered a new possibility to lead analytical researches based on a large amount of reports."

More >>

Semantic solutions: Categorizer | Summarizer | Comparator | Spell Checker | QAS

Products

Intellexer Categorizer

Intellexer Categorizer SDK

More about Categorizer

How Intellexer Categorizer Works

1. A user (administrator) creates a catalogue structure and defines categories

2. Etalon documents are selected for each category / subcategory on the base of which Categorizer forms a so-called fingerprint. Each category corresponds to the fingerprint

Fingerprint - is a set of main concepts (or terms) and relations between them, extracted from the etalon categories

3. Documents for categorization are parsed by Linguistic Processor which extracts syntactic and semantic relations from them

4. All documents presented in the form of semantic tree are compared with the fingerprints of each category. As a result of comparison, Intellexer Categorizer estimates the proximity degree for each document and category

5. The following categories are assigned for each document

a. High relevant categories
b. Low relevant categories
c. Irrelevant categories

To learn more about Categorizer principles of working, please visit Online Demo.