Probabilistic parsing for German using sister-head dependencies
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Is it harder to parse Chinese, or the Chinese Treebank?
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Is it really that difficult to parse German?
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Discontinuity revisited: an improved conversion to context-free representations
LAW '07 Proceedings of the Linguistic Annotation Workshop
A dependency-based method for evaluating broad-coverage parsers
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Data-driven parsing using probabilistic linear context-free rewriting systems
Computational Linguistics
Hi-index | 0.00 |
Recent parsing research has started addressing the questions a) how parsers trained on different syntactic resources differ in their performance and b) how to conduct a meaningful evaluation of the parsing results across such a range of syntactic representations. Two German treebanks, Negra and TüBa-D/Z, constitute an interesting testing ground for such research given that the two treebanks make very different representational choices for this language, which also is of general interest given that German is situated between the extremes of fixed and free word order. We show that previous work comparing PCFG parsing with these two treebanks employed PARSEVAL and grammatical function comparisons which were skewed by differences between the two corpus annotation schemes. Focusing on the grammatical dependency triples as an essential dimension of comparison, we show that the two very distinct corpora result in comparable parsing performance.