Logo da USCProLNat


DepPattern toolkit (also in github) is a linguistic package providing a grammar compiler, PoS taggers, and dependency based parsers for several languages. It's provided with an user guide (pdf).

The compiler, named 'compi', was implemented in Ruby. It generates parsers in PERL from DepPattern grammars. To write formal grammars using the formalism ”DepPattern”, please, look up the tutorial (pdf).

In addition, DepPattern is provided with parsers for 5 languages: English, Spanish, Galician, French, and Portuguese. The parsers were implemented in PERL and are stored in the directory “parsers”.

Three demos are available: a basic demo allowing some sentences to be analyzed, a grammar-based demo where the user inserts his/her own grammar, and advanced demo to analyze text files.

Software download

Click here to download DepPattern (a more recent version available at github), a toolkit containing both multilingua natural language parsers implemented with Perl and a compiler implemented in ruby. Machine requirements are the following:

Click here to download the different grammars and source files we have written so far. In order the grammars to be compiled into the corresponding parsers, please follow the user guide.

How to install

# tar xzvf DepPattern.tgz
# cd DepPattern
# sh install-DepPattern.sh

How to use

# sh dp.sh
Syntax: dp.sh type_of_output tagger lang file [parser] [grammar]

type_of_output= -a (analysis), -fa (full analysis) -c (tagged text)
tagger= freeling, treetagger
language= gl, es, en, pt, fr
file= path of the file input
parser= path of the parser, or name of the parser generated from grammar
grammar= path of the file grammar

Read the user guide to both how to install and how to use the DepGrammar toolkit.

Valid HTML 4.01 Strict Valid CSS!