A4 Refereed article in a conference publication
Mind the Gap: Data Enrichment in Dependency Parsing of Elliptical Constructions
Authors: Kira Droganova, Filip Ginter, Jenna Kanerva, Daniel Zeman
Editors: Marie-Catherine de Marneffe, Teresa Lynn, Sebastian Schuster
Conference name: Universal Dependencies Workshop
Publication year: 2018
Book title : Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
First page : 47
Last page: 54
ISBN: 978-1-948087-78-0
Web address : http://aclweb.org/anthology/W18-6006
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/37617276
In this paper, we focus on parsing rare and
non-trivial constructions, in particular ellipsis. We report on several experiments in
enrichment of training data for this specific
construction, evaluated on five languages:
Czech, English, Finnish, Russian and Slovak.
These data enrichment methods draw upon
self-training and tri-training, combined with
a stratified sampling method mimicking the
structural complexity of the original treebank.
In addition, using these same methods, we
also demonstrate small improvements over the
CoNLL-17 parsing shared task winning system for four of the five languages, not only restricted to the elliptical constructions.
Downloadable publication This is an electronic reprint of the original article. |  |
