Semantex™


Semantex Internal Architecture

Semantex™ is an enterprise-class information extraction system that supports the automatic or semi-automatic analysis of large volumes of electronic information in order to detect entities, attributes, relationships and events. Semantex™ represents a hybrid model for information extraction, combining machine-learning and grammatical approaches to achieve better results than any of the techniques could individually.


Semantex™ is modular, scalable and portable to various domains of interest and is used to power both commercial and intelligence applications. It can exploit multiple processors to achieve the throughput necessary for high-volume environments typically encountered in data-intensive government applications. The XML output reflects the rich features assigned to elements of the text based on syntactic and semantic knowledge.


Benefits

  • Time Savings
    • Reduce time to evaluate critical information
    • Increase productivity of key personnel
  • System Productivity
    • Distributed architecture increases throughput
    • Grows with increasing volume requirements
  • Information Discovery
    • Profiles allow tracking of associated information
    • Quickly identifies obscure or hidden relationships
  • Tight Integration with Search
    • Works with any search engine index
    • Combine keyword search with text analytics
  • Domain Customization
    • Optimizes extraction of relevant information
    • Rapid adaptation to changing circumstances
  • Supports a Variety of Data Sources & Formats
    • FBIS, USMTF, HUMINT, Dialog, Lexis-Nexis, Factiva, etc.

Differentiators

  • Profiles
    • One profile for each unique entity identified
    • Pulls together all related information
  • Events
    • Detailed extraction of events, including participants, actions and details
    • Resolves time information into standard date and/or time
  • Hybrid Processing Model
    • Uses most appropriate technology at each processing stage
    • Best quality results by minimizing compounding variances
  • Customizability
    • Configurable architecture and customization tools simplify domain porting
    • Non-linguists can customize text analytics capabilities
  • Scalability
    • Designed from the beginning as a distributed solution
    • Individual processing modules can be configured differently