A Fast, Accurate, Non-Projective, Semantically-Enriched Parser
This page links to code related to the parsing system described in the following paper:
Stephen Tratz and Eduard Hovy. 2011. A Fast, Accurate, Non-Projective, Semantically-Enriched Parser. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Edinburgh, Scotland, UK.
This includes a newer version of the preposition sense disambiguation module previously described by:
Dirk Hovy, Stephen Tratz, and Eduard Hovy. 2010. What's in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class. In Proceedings of COLING 2010: Poster Volume. Beijing, China.
Stephen Tratz and Dirk Hovy. 2009. Disambiguation of Preposition Sense using Linguistically Motivated Features. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Student Research Workshop and Doctoral Consortium. Boulder, Colorado.
Also included is a newer version of the noun compound interpretation module based on the system described by:
Stephen Tratz and Eduard Hovy. 2010. A Taxonomy, Dataset, and Classifier for Automatic Noun Compound Interpretation. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden.
There are also modules for interpretation of possessives, PropBank-style semantic role labeling, and part-of-speech tagging.
More discussion of the parsing system and its various components may be found in Stephen Tratz's thesis once it becomes available.
The code is provided under the Apache License 2.0.
License (Apache 2.0)
Current version: 0.2.2