NAME

Lingua::Interset::Tagset::CS::Conll2009 - Driver for the Czech tagset of the CoNLL 2009 Shared Task.

VERSION

version 3.014

SYNOPSIS

  use Lingua::Interset::Tagset::CS::Conll2009;
  my $driver = Lingua::Interset::Tagset::CS::Conll2009->new();
  my $fs = $driver->decode("N\tSubPOS=N|Gen=M|Num=S|Cas=1|Neg=A");

or

  use Lingua::Interset qw(decode);
  my $fs = decode('cs::conll2009', "N\tSubPOS=N|Gen=M|Num=S|Cas=1|Neg=A");

DESCRIPTION

Interset driver for the Czech tagset of the CoNLL 2009 Shared Task. CoNLL 2009 tagsets in Interset are traditionally two values separated by tabs. The values come from the CoNLL 2009 columns POS and FEAT. For Czech, these values are derived from the tagset of the Prague Dependency Treebank; however, there is an additional surface feature Sem, which is derived from PDT lemmas. The CoNLL 2009 tagset differs slightly from CoNLL 2006 and 2007: the (fine-grained) POS column of 2006 and 2007 has been moved to the FEAT column as a new feature called SubPOS. This driver is a translation layer above the cs::conll driver.

SEE ALSO

Lingua::Interset, Lingua::Interset::Tagset, Lingua::Interset::Tagset::CS::Pdt, Lingua::Interset::Tagset::CS::Conll, Lingua::Interset::FeatureStructure

AUTHOR

Dan Zeman <zeman@ufal.mff.cuni.cz>

COPYRIGHT AND LICENSE

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.