Retina API, English language processing, Cortical.io, Vienna, Austria

[Airicist]

Developer - Cortical.io (https://pr.ai/showthread.php?13764)

Home page - cortical.io/api.html (https://www.cortical.io/api.html)

[Airicist]

https://youtu.be/YZTuM9ze870

The Cortical Engine for Processing Text

Published on Mar 15, 2013


The CEPT-Retina produces semantic fingerprints of language and thereby represents a new fundamental alternative to capture the inner semantics of natural language. These fingerprints can represent words, documents or the information needs of users. This approach helps get more relevant search results and classify information more efficiently. The CEPT-Retina also enables the making of intelligent decisions based on human-generated text input.

Words can be represented as fingerprints

A picture of cats or dogs represents a good example of a traditional semantic fingerprint. An audio recording would be another example that captures a different (audio) dimension. These kinds of semantic representation are handled by image resp. sound analysis, a process that is computationally intensive but feasible for some applications.

From Symbols to Numeric representations

The words CAT and DOG are symbolic representations of the entities of cats and dogs. To give meaning to these symbols, we need a dictionary as we are unable to interpret the representations on themselves. The CEPT-Retina transforms the symbol for CAT into its semantic fingerprint shown below in red, the same for DOG shown in blue. The overlay of the 2 fingerprints enables direct (visual) comparison of semantic relatedness. Therefore, we refer to them as semantic fingerprints.