Treex::Block::W2A::EN::Tokenize - rule-based tokenization
Each sentence is split into a sequence of tokens using a series of regexs. Flat a-tree is built and attributes
no_space_after are filled. This class uses English specific regex rules (insipred by PennTB) for tokenization of contractions like He's, we'll, they've, don't etc.
David Mareček <email@example.com>
Martin Popel <firstname.lastname@example.org>
Copyright © 2011 by Institute of Formal and Applied Linguistics, Charles University in Prague
This module is free software; you can redistribute it and/or modify it under the same terms as Perl itself.