TY - CHAP U1 - Konferenzveröffentlichung A1 - Kübler, Sandra A1 - Maier, Wolfgang A1 - Rehbein, Ines A1 - Versley, Yannick ED - Calzolari, Nicoletta ED - Choukri, Khalid ED - Maegaard, Bente ED - Mariani, Joseph ED - Odijk, Jan ED - Piperidis, Stelios ED - Tapias, Daniel T1 - How to Compare Treebanks T2 - Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC-2008), May, 28-30, 2008. Marrakech, Marocco N2 - Recent years have seen an increasing interest in developing standards for linguistic annotation, with a focus on the interoperability of the resources. This effort, however, requires a profound knowledge of the advantages and disadvantages of linguistic annotation schemes in order to avoid importing the flaws and weaknesses of existing encoding schemes into the new standards. This paper addresses the question how to compare syntactically annotated corpora and gain insights into the usefulness of specific design decisions. We present an exhaustive evaluation of two German treebanks with crucially different encoding schemes. We evaluate three different parsers trained on the two treebanks and compare results using EVALB, the Leaf-Ancestor metric, and a dependency-based evaluation. Furthermore, we present TePaCoC, a new testsuite for the evaluation of parsers on complex German grammatical constructions. The testsuite provides a well thought-out error classification, which enables us to compare parser output for parsers trained on treebanks with different encoding schemes and provides interesting insights into the impact of treebank annotation schemes on specific constructions like PP attachment or non-constituent coordination. KW - Korpus KW - Syntaktische Analyse KW - Evaluation methodologies KW - Parsing Systems KW - Syntax Y1 - 2008 U6 - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-57520 UN - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-57520 UR - http://www.lrec-conf.org/proceedings/lrec2008/ SN - 2-9517408-4-0 SB - 2-9517408-4-0 SP - 2322 EP - 2329 PB - European Language Resources Association CY - Paris ER -