Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
linguisticsweb:tutorials:linguistics_tutorials:automaticannotation:treetagger [2014/02/07 16:37]
sabinebartsch created
linguisticsweb:tutorials:linguistics_tutorials:automaticannotation:treetagger [2014/05/15 09:50]
sabinebartsch
Line 1: Line 1:
 ====== TreeTagger ====== ====== TreeTagger ======
 +
 +The [[http://​www.cis.uni-muenchen.de/​~schmid/​tools/​TreeTagger/​|TreeTagger]] is a language independent probabilistic part of speech tagger. It has been applied to the following languages for which modells exist:
 +
 +German, English, French, Italian, Dutch, Spanish, Bulgarian, Russian, Portuguese, Galician, Chinese, Swahili, Slovak, Latin, Estonian and Old French
 +
 +
 +====== TreeTagger for Windows ======
 +
 +Download the Windows version of the TreeTagger from:
 +
 +http://​www.cis.uni-muenchen.de/​~schmid/​tools/​TreeTagger/​data/​tree-tagger-windows-3.2.zip
 +
 +Unpack the zip-archive to the directory:
 +
 +''​C:​\TreeTagger''​
 +
 +
 +Next, download the parameter files for the languages you want to tag from the list of model files on the TreeTagger homepage. Make sure you select the appropriate files for your operating system; for Windows these are listed under:
 +
 +**Parameter files for PC (Linux, Windows, and Mac-Intel)**
 +
 +Unpack these to the TreeTagger sub-directory ​
 +
 +''​C:​\TreeTagger\lib''​
 +
 +You are now set to tag.
 +
 +Navigate to the directory ''​C:​\TreeTagger\bin''​
 +
 +To tag an English text, type in tag-english.bat plus the file name of a file you want to tag and watch the result flicker on your screen.
 +
 +
 +
 +====== TreeTagger for MacOS X and UNIX-like OSes ======
 +
 +Download tagger package and tagging scripts plus the installation script from the TreeTagger page. Put them into a directory ''/​TreeTagger''​
 +
 +Do not unpack any of the files. ​
 +Navigate to this directory and execute the installation script by typing
 +
 +''​bash install-tagger.sh''​
 +
 +To save you from having to always type the entire TreeTagger path, add the TreeTagger sub-directories ​
 +
 +''​TaggerDirectory/​bin''​
 +
 +and
 +
 +''​TreeTaggerDirectory/​cmd''​
 +
 +to the PATH variable of the operating system. To do this type:
 +
 +''​$ PATH=$PATH:/​PathToTreeTaggerDirecory/​bin:/​PathToTreeTaggerDirecory/​cmd
 +$ export PATH
 +''​
 +To check that this has actually happened type:
 +
 +''​echo $PATH''​
 +
 +===== Tagging with the TreeTagger =====
 +
 +In order to tag with the TreeTagger, the call looks basically like this:
 +
 +''​tree-tagger -options- <​parameter file> <input file> <output file>''​
 +
 +To test whether the TreeTagger actually tags your text, type:
 +
 +''​tree-tagger -token German.par input.txt output.txt''​
 +