Home
Applications
Products Overview
Federated Search
Inxight SmartDiscovery Awareness Server
Text Analysis
Inxight SmartDiscovery Extraction Server
Data Cleansing
Inxight SmartDiscovery Metadata Management System
Visualization
Inxight SmartDiscovery VizServer
Development Kits
Inxight LinguistX Platform
Inxight ThingFinder
Inxight StarTree
Inxight TimeWall
Inxight TableLens
Inxight Summarizer
Contact us at:
2355 Dulles Corner Boulevard, Suite 525
Herndon, Virginia 20171-3402
Phone: 703.713.3930
sales@inxightfedsys.com
The following components work together to make Inxight SmartDiscovery Extraction Server the most advanced information extraction and analysis tool available today.

World-Class Natural-Language Processing
Inxight’s advanced linguistics capabilities go beyond translating and can actually “understand” documents in more than 30 major languages. Through sophisticated Natural Language Processing (NLP), Inxight LinguistX® Platform knows how verbs, nouns and other language structure interact and are unique to each language. Unlike a search engine, SmartDiscovery Extraction Server literally understands the meaning and context of information, not just the words themselves.

Powerful Entity Extraction and Analysis
As the name implies, Inxight ThingFinder® finds things and relationships. With more than 35 out-of-the-box entities, relations, and events pre-configured with the system, SmartDiscovery Extraction Server extracts key information – the who, what, where, when, and how in text – automatically on-the-fly and reveals important relations and events occurring between those things. Relations that are not implicit in one document or source are uncovered because ThingFinder understands what you are looking for and can put the disparate bits and pieces together. An intuitive Workbench makes it easier to create and test your custom pattern-based and list-based entities, relations and events.

Taxonomy-based Document Categorization
Using a search engine to find relevant information for conceptual categories like “unrest, politics, or environmental issues” will result in thousands of pages of non-relevant information. Inxight Categorizer™ provides taxonomy-based document level classification of information that is not implicit within the document; for example, a document might belong to a sports category in spite of the fact that the word “sports” never appears in the text. But any document that talks about baseball, for instance, is certainly a document about sports, regardless of whether “sports” occurs in the document. Categorizer understands these types of conceptual relationships and will automatically classify information in the right category. An intuitive Categorizer Workbench makes it easier to create, import and test your taxonomies using a hybrid learn-by-example and rules-based approach.

Automatic Document Summaries
Inxight Summarizer™ extracts and analyzes the most relevant sentences to create a summary of any document or set of documents. Think of it as an “automated abstract creator” that reads the information and creates an executive report on the content. Summarizer digests the general substance of the information by using a system of weighted sentences, generally giving more weight to the first and last sentences of a paragraph, for example, along with the specific query parameters of your search.

This is important because one person may be investigating weather phenomenon and be interested in “snow,” whereas someone else may use the same document to investigate transportation patterns of long-haul trucks. Summarizer understands your specific requirements and will weight the summary differently depending on your area of interest.

Overview
Features
Technical Specs