Table of Contents
The amount of enterprise information is growing dramatically. Unstructured data account for 80-90% of this information. They are often untagged, organized according to personal preferences, written according to the language and terminology preferences of the author, and thus hard to find and manage.
A result of many years of intensive R&D, ABBYY language technologies allow better understanding of unstructured document content, offering robust solutions to many long-standing language processing problems of the information age.
- Comprehensive text analysis: information monitoring, sentiment analysis, controlling access to confidential information, and summarizing and annotating documents
- Efficient handling of text documents: classification, filtering, text comparison
Linguistic Analysis Results
Below you can see the Compreno linguistic result of the short sentence:
John bought a car from Mark
- You can see that the Persons were identified
- The grammatical info/features of every word were detected
- The information is provided as XML, so that it can be used in other applications.
Entities and Fact Results
The same sentence processed in ABBYY InfoExtractor.
- The fact that this sentence is about “PurchaseAndSale” was detected
- The object was detected
- The two involved persons were identified
- The information is provided as RDF/XML, so that it can be used in other semantic applications
Semantic analysis of a sentence