The language of the input text or web page is determined based on profiles for supported languages. Distinguishing features of each language are extracted and used with a Bayesian filter to detect the input language.
The Cortical.io Retina technology is accessed via a REST API. To detect language and create semantic fingerprints, you can include the following API calls in your application:
/text/detect: language endpoint: Can identify more than 50 language
/text endpoint: Generates a semantic fingerprint for inputted text
To begin to integrate Cortical.io services into your application, register for a free API key.
To detect the language of text or of a web page, follow the instructions on the screen. The system can identify over 50 languages.
To view an example of language detection, at the bottom of the input area, select an example.
If the input text or web page is in Arabic, Chinese, Danish, English, French, German, Russian, or Spanish, the meaning of the text or web page is encoded numerically as a semantic fingerprint, which is displayed graphically as a grid.
To view a larger fingerprint, above the fingerprint, click the double-arrow icon.
Every dot on a semantic fingerprint represents a collection of terms that are associated with one another. You can view some of the terms that are located at any of the blue dots on the grid by hovering over that dot. Dots that are close to one another on the grid are also close in meaning. Together, all blue dots on the grid represent the meaning of the inputted text or web page.