Ines Rehbein
Leibniz ScienceCampus, Institut für Deutsche Sprache Mannheim, Germany
Julius Steen
Leibniz ScienceCampus, Universität Heidelberg, Germany
Bich-Ngoc Do
Leibniz ScienceCampus, Universität Heidelberg, Germany
Anette Frank
Leibniz ScienceCampus, Universität Heidelberg, Germany
Download article
Published in: Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017), September 18-20, 2017, Università di Pisa, Italy
Linköping Electronic Conference Proceedings 139:25, p. 218-228
Published: 2017-09-13
ISBN: 978-91-7685-467-9
ISSN: 1650-3686 (print), 1650-3740 (online)
Universal Dependency (UD) annotations, despite their usefulness for cross-lingual tasks and semantic applications, are not optimised for statistical parsing. In the paper, we ask what exactly causes the decrease in parsing accuracy when training
a parser on UD-style annotations and whether the effect is similarly strong for all languages. We conduct a series of experiments where we systematically modify individual annotation decisions taken
in the UD scheme and show that this results in an increased accuracy for most, but not for all languages. We show that the encoding in the UD scheme, in particular the decision to encode content words as heads,
causes an increase in dependency length for nearly all treebanks and an increase in arc direction entropy for many languages,
and evaluate the effect this has on parsing accuracy.
