ACL 2016 paper version

This version corresponds to the ACL 2016 paper version. It is very basic. It lacks documentation. ...

How to cite:

Matthieu Constant and Joakim Nivre (2016). A Transition-based System for Joint Lexical and Syntactic Analysis. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL’16). Berlin, Germany. August. pp. 161 – 171.

Reproducibility of ACL paper experiments

We carried out our experiments on two different datasets annotating both the syntactic structure and the MWEs, derived from

• the French Treebank (Abeille et al., 2003),
• the STREUSLE 2.0 corpus (Schneider et al., 2014b) combined with the English Web Treebank (Bies et al., 2012)

Since the French Treebank and the English Web treebank cannot be distributed on free public download, the two datasets will be provided upon request to Mathieu.Constant@univ-lorraine.fr (on condition that the applicant holds licenses for both treebanks). At the same time, we will also provide scripts to learn and evaluate parsing models as in the ACL 2016 paper.

References

Anne Abeille, Lionel Clément, and François Toussenel. 2003. Building a treebank for French. In Anne Abeille, editor, Treebanks. Kluwer, Dordrecht.

Ann Bies, Justin Mott, Colin Warner, and Seth Kulick. 2012. English web treebank LDC2012T13.

Nathan Schneider, Spencer Onuffer, Nora Kazour, Emily Danchik, Michael T. Mordowanec, Henrietta Conrad, and Noah A. Smith. 2014. Comprehensive Annotation of Multiword Expressions in a Social Web Corpus. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 455–461, Reykjavik, Iceland, May. ELRA