IMSTrans

IMSTrans is a transition-based dependency parser. The parser implements the (labeled) ArcStandard system including a swap transition allowing for non-projective structures following Nivre (2009). It can be used to train both greedy parsers and globally optimized beam-search parsers. The parser was developed for the paper Björkelund & Nivre (2015) and implements all the non-deterministic oracles discussed in that paper. The parser was also used in the paper by Falenská et al. (2015).

The parser was further developed for the Björkelund et al. (2016) paper on joint sentence splitting and parsing.

• Anders Björkelund and Joakim Nivre. 2015. Non-deterministic oracles for unrestricted non-projective transition-based dependency parsing. In Proceedings of the 14th International Conference on Parsing Technologies. [pdf] [bibtex] [slides]
  
  
• Agnieszka Falenská, Anders Björkelund, Özlem Çetinoğlu, and Wolfgang Seeker. Stacking or Supertagging for Dependency Parsing -- What's the Difference? In Proceedings of the 14th International Conference on Parsing Technologies. [pdf] [bibtex] [slides]
  
  
• Anders Björkelund, Agnieszka Faleńska, Wolfgang Seeker, and Jonas Kuhn. How to Train Dependency Parsers with Inexact Search for Joint Sentence Boundary Detection and Parsing of Entire Documents. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [pdf] [bib] [poster] [code]

The binaries and source code for the old version (2015, version 1.0) can be downloaded here.
The binaries and source code for the joint system (2016, version 2.0) can be downloaded here.