TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Rehbein, Ines
A1  - Steen, Julius
A1  - Do, Bich-Ngoc
A1  - Frank, Anette
ED  - Montemagni, Simonetta
ED  - Nivre, Joakim
T1  - Universal Dependencies are hard to parse – or are they?
T2  - Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017). September 18-20, 2017 Università di Pisa Istituto di Linguistica Computazionale “A. Zampolli”, CNR Pisa
N2  - 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.
T3  - Linköping Electronic Conference Proceedings - 139 
KW  - Syntax
KW  - Annotation
KW  - Parser
KW  - Universalgrammatik
Y1  - 2017
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-80232
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-80232
UR  - http://aclweb.org/anthology/W17-6525
SN  - 978-91-7685-467-9
SB  - 978-91-7685-467-9
SP  - 218
EP  - 228
PB  - Linköping University Electronic Press
CY  - Linköping, Schweden
ER  -