TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Rehbein, Ines
A1  - van Genabith, Josef
ED  - Nivre, Joakim
ED  - Kaalep, Heiki-Jaan
ED  - Muischnek, Kadri
ED  - Koit, Mare
T1  - Evaluating Evaluation Measures
T2  - Proceedings of the 16th Nordic Conference of Computational Linguistics (NODALIDA-2007). University of Tartu, Tartu. May 24-26, 2007
N2  - This paper presents a thorough examination of the validity of three evaluation measures on parser output. We assess parser performance of an unlexicalised probabilistic parser trained on two German treebanks with different annotation schemes and evaluate parsing results using the PARSEVAL metric, the Leaf-Ancestor metric and a dependency-based evaluation. We reject the claim that the TüBa-D/Z annotation scheme is more adequate then the TIGER scheme for PCFG parsing and show that PARSEVAL should not be used to compare parser performance for parsers trained on treebanks with different annotation schemes. An analysis of specific error types indicates that the dependency-based evaluation is most appropriate to reflect parse quality.
KW  - Korpus <Linguistik>
KW  - Syntaktische Analyse
KW  - Deutsch
Y1  - 2007
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-57543
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-57543
SN  - 978-9985-4-0513-0
SB  - 978-9985-4-0513-0
SP  - 372
EP  - 379
PB  - University of Tartu
CY  - Tartu
ER  -