MaltParser is a 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.
F# Batchfile
Switch branches/tags
Nothing to show
Latest commit c26324f Aug 27, 2016 @sergey-tihon sergey-tihon Migration to 1.9.0
Permalink
Failed to load latest commit information.
.paket
docs
nuget
.gitattributes Initial commit May 31, 2014
.gitignore
LICENSE.txt
MaltParser.sln Migration to v1.8.1 Jul 15, 2015
README.md
RELEASE_NOTES.md Migration to 1.9.0 Aug 27, 2016
appveyor.yml
build.cmd Migration to v1.8.1 Jul 15, 2015
build.fsx Migration to 1.9.0 Aug 27, 2016
paket.dependencies
paket.lock

README.md

Build status

MaltParser for .NET NuGet Status

MaltParser is a 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 is developed by Johan Hall, Jens Nilsson and Joakim Nivre at Växjö University and Uppsala University, Sweden.

MaltParser implements nine deterministic parsing algorithms:

  • Nivre arc-eager
  • Nivre arc-standard
  • Covington non-projective
  • Covington projective
  • Stack projective
  • Stack swap-eager
  • Stack swap-lazy
  • Planar (implemented by Carlos Gómez-Rodríguez)
  • 2-planar (implemented by Carlos Gómez-Rodríguez)

MaltParser allows users to define feature models of arbitrary complexity.

MaltParser currently includes two machine learning packages (thanks to Sofia Cassel for her work on LIBLINEAR):

  • LIBSVM - A Library for Support Vector Machines (Chang, 2001).
  • LIBLINEAR -- A Library for Large Linear Classification (Fan et al., 2008).

MaltParser can also be turned into a phrase structure parser that recovers both continuous and discontinuous phrases with both phrase labels and grammatical functions (Hall and Nivre, 2008a; Hall and Nivre, 2008b).