Language identification engines

Language identification engines analyze text to deduce the language most likely being used in the text.

Engine input

Language identification engines can specify supportedInputFormats in their manifest for mime types they can support natively (e.g. text/plain, application/pdf). In this case, engines are given the entire file as their input and are responsible for outputting the language analysis results for the entire file in their vtn-standard output.

Engine output

Languages are specified according to the language validation contract by specifying the language key on the entire document.

[Tip] All language codes should conform to the BCP-47 specification.

See the language validation contract json-schema.

Example

This example shows categorizing an entire document according to one language.

{
  "validationContracts": ["language"],
  "language": "en-US"
}

• Learn about AION.
• See the cognitive engine classes.
• See an overview of cognitive technology.
• View engines for your media type.

• Using aiWARE
• Use cognitive engines
• Choose an engine
• Capability
• Text
• Language identification