@InProceedings{Frank:2001,
AUTHOR = {Frank, Anette},
TITLE = {Treebank Conversion. Converting the NEGRA Treebank to an LTAG Grammar},
YEAR = {2001},
BOOKTITLE = {Proceedings of the Workshop on Multi-layer Corpus-based Analysis. Workshop held as part of the EUROLAN 2001 Summer Institute on Creation and Exploitation of Annotated Language Resources, July 30 - August 11},
ADDRESS = {Iasi, Romania},
URL = {http://www.dfki.de/~frank/papers/tbc-eurolan01.pdf},
ABSTRACT = {We present a method for rule-based structure conversion of existing treebanks, which aims at the extraction of linguistically sound, corpus-based grammars in a specific grammatical framework. We apply this method to the NEGRA treebank to derive an LTAG grammar of German. We describe the methodology and tools for structure conversion and LTAG extraction. The conversion and grammar extraction process imports linguistic generalisations that are missing the in original treebank. This supports the extraction of a linguistically sound grammar with maximal generalisation, as well as grammar induction techniques to capture unseen data in stochastic parsing. We further illustrate the flexibility of our conversion method by deriving an alternative representation in terms of topological field marking from the NEGRA treebank, which can be used as input for stochastic topological parsing approaches. On a broader perspective our approach contributes to a better understanding on where corpuslinguistics and theoretical linguistics can meet and enrich each other.},
ANNOTE = {COLIURL : Frank:2001:TCC.pdf}
}
|
