论文信息 - Dependency and Phrasal Parsers of the Czech Language: A Comparison

Dependency and Phrasal Parsers of the Czech Language: A Comparison

In the paper, we present the results of an experiment with comparing the effectiveness of real text parsers of Czech language based on completely different approaches - stochastic parsers that provide dependency trees as their outputs and a meta-grammar parser that generates a resulting chart structure representing a packed forest of phrasal derivation trees. We describe and formulate main questions and problems accompanying such experiment, try to offer answers to these questions and finally display also factual results of the tests measured on 10 thousand Czech sentences.

Ales Horák | Vojtech Kovár | Vladimír Kadlec | Tomás Holan

[1] Keith Hall,et al. Corrective Modeling for Non-Projective Dependency Parsing , 2005, IWPT.

[2] Ales Horák,et al. Enhancing Best Analysis Selection and Parser Comparison , 2002, TSD.

[3] Ales Horák,et al. Best Analysis Selection in Inflectional Languages , 2002, COLING.

[4] Ales Horák,et al. New Meta-grammar Constructs in Czech Language Parser synt , 2005, TSD.

[5] Geoffrey Sampson,et al. A proposal for improving the measurement of parse accuracy , 2000 .

[6] Zdenek Zabokrtský,et al. Combining Czech Dependency Parsers , 2006, TSD.

[7] Joakim Nivre,et al. Graph Transformations in Data-Driven Dependency Parsing , 2006, ACL.

[8] Geoffrey Sampson,et al. A test of the leaf-ancestor metric for parse accuracy , 2003, Natural Language Engineering.

[9] Beth Ann Hockey,et al. Grammar & Parser Evaluation in the XTAG Project , 1998 .

[10] Michael Collins,et al. A Statistical Parser for Czech , 1999, ACL.

[11] Jan Haji. Complex Corpus Annotation: The Prague Dependency Treebank , 2005 .

[12] Jan Hajic. Disambiguation of Rich Inflection - Computational Morphology of Czech , 2004 .

[13] Fernando Pereira,et al. Discriminative learning and spanning tree algorithms for dependency parsing , 2006 .