Create your services once. See them work automatically in all languages.

The Semantic Folding Engine is offered through an API and deployed using a Software-as-a-Service model. This approach has the advantage of keeping
the lab-to-market time to the minimum. It is our declared goal to make it as easy as possible to experiment and adopt this fundamentally new

As soon as you have made yourself familiar with this new approach to natural language processing, a wide variety of functionalities can be implemented intuitively, without needing any knowledge in linguistics. We
provide a growing number of client-SDKs to allow easy integration in various application environments.

10 reasons that speak for’s technology:

  • Develop your application in English and use it right away in all other available languages.
  • Start immediately -no special knowledge is required, our technology is intuitive.
  • You don’t even need to tune the system nor enter linguistic parameters.
  • Offer your users a better search experience: higher precision and less noise.
  • Increase the search efficiency with contextualized keyword generation.
  • Easily automate actions based on user content - give your applications language intelligence!
  • Harness the power of automated semantic document processing.
  • Understand what your users want and personalize your applications on the fly.
  • Surf on the top of the AI-wave by adopting a rapidly growing technology stack.
  • Rely on our transparent development process to comfortably plan your product.

Technology Stack

CEPT Technology Stack

The Retina

  • is the central component of the Semantic Folding Engine.
  • captures the essence of language.
  • learns about a specific language by reading/processing relevant text content, be it Spanish or Chinese, or domain specific terminology (e.g. medical terminology).
  • depending on the text content chosen, the Retina will have specific knowledge of a language or domain.

To begin with, we have produced generic retinas (English, French, German…) by ingesting the respective Wikipedias. New input in
these Wikipedias is automatically assimilated. This guarantees that the Retina evolves along with living languages and continuously
captures the transformation of their socio-cultural context. A retina can be specialized in specific topics or domain language, which increases the precision
of your NLP.

12 disciplines

The application fields of’s technology are endless. To systematically address specific domains we have structured our upcoming functionalities in what we call the 12 disciplines of language intelligence.
read more…

The Cortical Engine

The Cortical Engine for Processing Text provides the system with language intelligence through three main building blocks:

  • The Retina
  • The Expression Engine permits to create Boolean expressions using words based on their meaning. For example, it allows to state the equation Jaguar - Porsche = Tiger. Operators are AND, OR, XOR, NOT, SUB.
  • The Similarity Engine allows to compute the semantic distance between any two words.

And additional modules like:

  • Semantic Fingerprinting What is it?
  • Disambiguation: decomposition of any word into its senses.
  • Text: creation of document fingerprints, semantic document slicing and keyword extraction.

##Try our demos:’s foundational API is offered through a REST service callable from any application and enables you to:

  • Convert any piece of text into a semantic fingerprint (SFP)
  • Measure the semantic distance between SFPs
  • Get context terms to any SFP
  • Extract keywords from any text
  • “Find more like this” - querying
  • Use logic expressions to compute meanings
  • Disambiguate words and sentences
  • Classify any text into any classification scheme
  • Specify the class criteria just by describing them
  • Create user profiles based on user provided text content
  • Compare users interests
  • Filter and route social network messages in real-time, based on their content

Retina API