Samhammer.LanguageDetection

Detect the language of a text using naive a Bayesian filter with generated language profiles from Wikipedia abstract xml, 99% over precision for 53 languages. Original author: Nakatani Shuyo.


Keywords
nlp, language, identification, guessing, detection, detecting, detector
License
Apache-2.0
Install
Install-Package Samhammer.LanguageDetection -Version 2.0.0

Documentation

Language Detection

.NET Port of Language Detection Library for Java by @shuyo

Compatibility

.NET Framework 4.6.1 .NET Standard 2.0

Install

Add a reference to LanguageDetection.dll.

Use

using LanguageDetection;

Load all supported languages

LanguageDetector detector = new LanguageDetector();
detector.AddAllLanguages();
Assert.AreEqual("lav", detector.Detect("čau, man iet labi, un kā iet tev?"));

or a small subset

LanguageDetector detector = new LanguageDetector();
detector.AddLanguages("lav", "lit", "eng");
Assert.AreEqual("lav", detector.Detect("čau, man iet labi, un kā iet tev?"));

You can also change parameters

LanguageDetector detector = new LanguageDetector();
detector.RandomSeed = 1;
detector.ConvergenceThreshold = 0.9;
detector.MaxIterations = 50;

License

Apache 2.0

How to publish package