Is it really that difficult to parse German?

  • This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra and TüBa-D/Z treebanks. Experiments with the Stanford parser, which uses a factored PCFG and dependency model, show that, contrary to previous claims for other parsers, lexicalization of PCFG models boosts parsing performance for both treebanks. The experiments also show that there is a big difference in parsing performance, when trained on the Negra and on the TüBa-D/Z treebanks. Parser performance for the models trained on TüBa-D/Z are comparable to parsing results for English with the Stanford parser, when trained on the Penn treebank. This comparison at least suggests that German is not harder to parse than its West-Germanic neighbor language English.
Metadaten
Author:Sandra KüblerORCiDGND, Erhard Hinrichs, Wolfgang Maier
URN:urn:nbn:de:hebis:30-1110601
URL:http://cl.indiana.edu/~skuebler/papers/parsegerman.pdf
ISBN:1-932432-73-6
Document Type:Preprint
Language:English
Year of Completion:2006
Year of first Publication:2006
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2008/10/21
Page Number:9
Note:
Erschienen in: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006), Stroudsburg, PA : Association for Computational Linguistics, 2006, S. 111–119, ISBN: 1-932432-73-6
Source:http://jones.ling.indiana.edu/~skuebler/papers/parsegerman.pdf ; (in:) Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP 2006 - Sydney, 2006.
HeBIS-PPN:206767889
Institutes:keine Angabe Fachbereich / Extern
Dewey Decimal Classification:4 Sprache / 40 Sprache / 400 Sprache
Sammlungen:Linguistik
Linguistik-Klassifikation:Linguistik-Klassifikation: Computerlinguistik / Computational linguistics
Licence (German):License LogoDeutsches Urheberrecht