The Perl Toolchain Summit needs more sponsors. If your company depends on Perl, please support this very important event.

NAME

DTA::CAB::Analyzer::Morph::Helsinki - morphological analysis via Gfsm automata, for use with Helsinki-style transducers

SYNOPSIS

 use DTA::CAB::Analyzer::Morph::Helsinki;
 
 $morph = DTA::CAB::Analyzer::Morph::Helsinki->new(%args);
 $morph->analyze($tok);

DESCRIPTION

DTA::CAB::Analyzer::Morph::Helsinki is a simplified wrapper for DTA::CAB::Analyzer::Automaton::Gfsm which sets the following default options:

 ##-- analysis selection
 label => 'morph',        ##-- analysis output property
 wantAnalysisLo => 0,     ##-- don't output lower label paths
 tolower => 1,            ##-- bash input to lower-case

It also adds TAGH-style tag-extraction post-processing in its analyzeTypes() method.

Morphological transducers are available in HFST format for various languages from https://sourceforge.net/projects/hfst/files/resources/morphological-transducers/. In order to be used with this package, the HFST transducers must be converted to Gfsm format, and may require additional transducer-specific adjustments (e.g. alphabet conventions for tag-extraction heuristics).

AUTHOR

Bryan Jurish <moocow@cpan.org>

COPYRIGHT AND LICENSE

Copyright (C) 2016-2021 by Bryan Jurish

This package is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.24.1 or, at your option, any later version of Perl 5 you may have available.