Compound Term Processing

Compound term processing, still unique in the market, automatically generates multi-term metadata underpinning auto-classification and surfacing intelligent content in context

Core Technology   Overview   Core Technology Benefits 

Compound Term Processing

  • Compound term processing remains a breakthrough technology that can identify and weight multi-word concepts based on purely statistical analysis. Compound term processing understands the relationships between words but is independent of vocabulary, grammatical style, and language.

    Compound term processing eliminates the barriers of leveraging the value of unstructured and semi-structured content and is used for:

    • Enterprise and hybrid search
    • Records management
    • Elimination of data breaches
    • Migration
    • Content optimization
    • eDiscovery and FOIA
    • Litigation support
    • Content management
    • Metadata management
    • Secure collaboration
    • Knowledge management
    • Research
    • Business social
    • Text analytics and data mining
  • Compound term processing automatically generates multi-term metadata that represents a concept, subject area, or topic. This eliminates end user tagging, captures concepts from any repository in any environment, and auto-classifies the multi-term metadata to one or more taxonomies.

    Concept Searching


    Do you feel your current method of tagging content is generating meaningful and rich metadata?


    Have you ever calculated the hard and soft dollars you are spending on applications and resources to improve applications that lack accurate metadata?
    Would an enterprise metadata repository for information governance, compliance, and automatic workflow be of value to you?


    Would a solution that is easily installed, rapidly deployed, simply managed, and eliminates end user tagging, be important to you?
    Key Features

    Key Features

    Compound term processing technology is an adaptive and scalable technology platform that enables the identification and the correct weighting of concepts in unstructured text, affording the rapid creation of multi-term, conceptual metadata, which can be classified to organizationally-defined taxonomies. The tagging and auto-classification of content can be aligned to business goals and the metadata generated can be easily integrated with any third-party application or platform that can interface via web services.

    • Eliminates end user intervention in tagging and processing of content
    • Unique ability to generate complex, multi-term metadata, not based on phrases, proximity, keywords, or pre-configured taxonomies
    • Statistical not semantic, so highly scalable, adaptive, and performant
    • Improves search precision with no loss of recall – unique in the market
    • Does not require complex rules, document training sets for each term, and is not based on linguistics so the grammatical style of content is irrelevant
    • High degree of accuracy and consistency when using automated query expansion
    • Reduces productivity drain, through elimination of manual tagging content and automation of processes
    • Reduces organizational risk, as relevant and accurate information can be accessed on demand
    • Provides an enterprise metadata framework available to all applications, eliminating the option to purchase separate application solutions, reducing costs, implementation, and training
    • Reduces risk through automation of processes and enforcement of policies across an enterprise, and improves productivity and accuracy of information
    • Improves decision making, and identifies risk and opportunities, through information transparency
    Key Benefits

    Key Benefits

    Multi-term metadata is a key component of the enterprise metadata framework. Coupled with auto-classification and taxonomy tools, it reduces risk and addresses information governance and compliance. Compound term processing addresses information complexity, and can effectively increase information transparency and provide the ability to manage content, regardless of where it resides. By providing immediate and actionable visibility to all relevant content, decision making can be improved, risk minimized, and cost reduced. The optimal result is an enterprise metadata repository, containing a rich set of intelligent metadata that reflects the unique terminology and vocabulary of an organization.

    Core Technology Benefits 
    Concept Searching