MaltParser is a free and open source system for data-driven dependency parsing, which can be used to induce a parsing model from treebank data and to parse new data using an induced model.
MaltParser implements seven deterministic parsing algorithms:
· Nivre arc-eager
· Nivre arc-standard
· Covington non-projective
· Covington projective
· Stack projective
· Stack swap-eager
· Stack swap-lazy
MaltParser allows users to define feature models of arbitrary complexity.
Requirements:
· Java
What's New in This Release: [ read full changelog ]
Changes:
· Improved the performance of the liblinear learner interface.
· '_' character do not mean ignore dependency label in the TabReader.
· It is now possible to have file names with blanks.
· Better error message if a column is an empty string in TabReader.
· Corrected the StackProjective.xml feature model file.
Find us on Google+
