Mate Tools

Mate tools is a toolkit of statistical NLP tools comprising a lemmatizer, part-of-speech tagger, morphological tagger, dependency parser, and semantic role labeler. It includes two different dependency parsers, a graph-based parser [1], and a joint tagger and transition-based parser [2]. The semantic role labeler is described in [3]. The complete pipeline and its web interface is described in [4]. Sources, binaries, and pre-trained models for several languages are available at http://code.google.com/p/mate-tools/

Online demos are available for

• German
• English

[1] Bernd Bohnet. 2010. Top Accuracy and Fast Dependency Parsing is not a Contradiction. The 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China. [pdf] [bib]

[2] Bernd Bohnet and Joakim Nivre. 2012 A Transition-Based System for Joint Part-of-Speech Tagging and Labeled Non-Projective Dependency Parsing. EMNLP-CoNLL, pages 1455-1465, Jeju Island, Korea. [pdf] [bib]

[3] Anders Björkelund, Love Hafdell, and Pierre Nugues. Multilingual semantic role labeling. In Proceedings of The Thirteenth Conference on Computational Natural Language Learning (CoNLL-2009), pages 43--48, Boulder, June 4--5 2009. [pdf] [bib]

[4] Anders Björkelund, Bernd Bohnet, Love Hafdell, and Pierre Nugues. A high-performance syntactic and semantic dependency parser. In Coling 2010: Demonstration Volume, pages 33-36, Beijing, August 23-27 2010. [pdf] [bib]

See http://code.google.com/p/mate-tools/