NAME
Lingua::YALI - YALI - Yet Another Language Identifier.
VERSION
version 0.010_05
SYNOPSIS
The YALI package is collection of modules and tools for language identification.
Modules
Lingua::YALI::Examples - contains examples.
Lingua::YALI::LanguageIdentifier - is module for language identification capable of identifying 122 languages.
Lingua::YALI::Builder - is module for training custom language models.
Lingua::YALI::Identifier - allows to use own models for identification.
Tools
yali-language-identifier - tool for language identification with pretrained models
yali-builder - tool for building custom language models.
yali-identifier - tool for language identification with custom language models.
WHY TO USE YALI
Contains pretrained models for identifying 122 languages.
Allows to create own models, trained on texts from specific domain, which outperforms the pretrained ones.
It is based on published paper http://ufal.mff.cuni.cz/~majlis/yali/.
COMPARISON WITH OTHERS
Lingua::Lid can recognize 45 languages and returns only the most probable result without any weight.
Lingua::Ident requires training files, so it is similar to Lingua::YALI::LanguageIdentifier, but it does not provide any options for constructing models.
Lingua::Identify can recognize 33 languages but it does not allows you to use different models.
AUTHOR
Martin Majlis <martin@majlis.cz>
COPYRIGHT AND LICENSE
This software is Copyright (c) 2012 by Martin Majlis.
This is free software, licensed under:
The (three-clause) BSD License