Skip to main content

Tools for processing treebank trees

Project description

treetools is a collection of tools for processing constituency treebank trees. It contains algorithms for tree manipulation (such as removal of crossing branches), tree analysis, and grammar extraction.

treetools is being developed and maintained at the Department for Computational Linguistics at the Institute for Language and Information at the University of Düsseldorf, Germany (see The project is sponsored by Deutsche Forschungsgemeinschaft (DFG).

Author: Wolfgang Maier <>.



  • Python 2.7.3+

To install the latest release from the Python package index, type:

pip install treetools --user

To install the latest version clone the git repository and run:

python install --user

within the repository directory.

If you have superuser privileges and want to perform a system-wide installation, omit the –user option, respectively.



To run treetools, type:

treetools [subcommand] [parameters] [options]

Available subcommands are:

  • transform: Process treebank trees. Run transformations and convert between different formats.
  • grammar: Extract grammars for different parsers from treebanks.
  • treeanalysis: Analyze certain properties of treebank trees, such as, e.g., gap degree.

To get see the available parameters for a subcommand, type:

treetools [subcommand] --help

To get verbose help on available transformation algorithms, available options, etc., type:

treetools [subcommand] --usage


To attach the punctuation in TIGER and remove its crossing branches while converting it from TigerXML to a bracket format, type:

treetools transform tiger.xml tiger.preproc.xml --trans root_attach boyd_split negra_mark_heads boyd_split raising --src-format tigerxml --dest-format export

To extract the bare sentences (one per line) from a treebank in bracketed format, such as the Penn Treebank, type:

treetools transform treebank.brackets treebank.terminals --src-format brackets --dest-format terminals

To delete the traces and co-indexation from the Penn Treebank, type:

treetools transform ptb ptb.notrace --transform ptb_transform --src-format brackets --dest-format brackets

To extract an left-to-right binarized LCFRS with v1/h2 markovization in rparse format from an export-format treebank, type:

treetools grammar input_treebank output_grammar leftright --dest-format rcg --markov v:1 h:2


The code is released under the GNU General Public Licence (GPL) 3.0 or higher. The license texts can be found at at

Project details

Release history Release notifications

This version
History Node


History Node


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
treetools-0.2.0.tar.gz (33.7 kB) Copy SHA256 hash SHA256 Source None Jan 4, 2017

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page