Lingua::Interset::Tagset::CS::Ajka - Driver for the tagset of the Czech morphological analyzers Ajka and Majka (Masaryk University in Brno).
use Lingua::Interset::Tagset::CS::Ajka; my $driver = Lingua::Interset::Tagset::CS::Ajka->new(); my $fs = $driver->decode('k1gMnSc1');
use Lingua::Interset qw(decode); my $fs = decode('cs::ajka', 'k1gMnSc1');
Interset driver for the tagsets of the Czech morphological analyzers Ajka and Majka (from the Masaryk University in Brno).
Multiple different flavors of the tagset have been used in different tools. The Ajka analyzer was written by Radek Sedláček as part of his master thesis (1999). In 2009, a the tool was completely rewritten by Pavel Šmerk and it got a new name, Majka. It still used more or less the same tagset. In 2011, a significant revision of the tagset was announced; the new versiou should be called 2.0, the old tagset (all flavors) would be retroactively called 1.0. According to this numbering, the Czech lexical database that is available for download with Majka in July 2014 is still 1.0. That is also the version that this driver assumes.
For more on Ajka, see http://nlp.fi.muni.cz/projekty/ajka/ajkacz.htm. For more on the original tagset of Ajka, see http://nlp.fi.muni.cz/projekty/ajka/tags.pdf. For more on the proposed version 2.0 of the tagset (not covered by this driver), see http://raslan2011.nlp-consulting.net/program/paper05.pdf?attredirects=0.
Petr Pořízka, Markus Schäfer, Dan Zeman <email@example.com>
Dan Zeman <firstname.lastname@example.org>
This software is copyright (c) 2019 by Univerzita Karlova (Charles University).
This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself.