Pre-trained MaltParser models

For users who only want to have a decent robust dependency parser (and who are not interested in experimenting with different parsing algorithms, learning algorithms and feature models), we provide pretrained parsing models for a selection of languages. Note, however, that the parser presupposes that the input has been segmented and annotated in accordance with the format of the original training set (see details for each parser).

Parser ModelLanguageTreebankMaltParser VersionLast update
engmaltEnglishPenn Treebank1.7 or laterMarch 12 2012
fremaltFrenchFrench Treebank1.7 or laterMarch 12 2012
swemaltSwedishSwedish Treebank1.7.2 or laterSeptember 25 2012

Note: These models can be used for research purposes provided that you have a license for the treebank on which the model was trained. If you want to use them for commercial applications, please contact the license holder for the relevant treebank to find out which conditions apply.

Contributed MaltParser models

Below we provide links to MaltParser models made available by other research groups.

Parser ModelLanguageTreebankContributorMaltParser VersionLast update
espmaltSpanishIULA TreebankIULA, Universitat Pompeu Fabra, Barcelona1.7 or later26 February 2013