Statistical parsing with an automatically-extracted tree adjoining grammar
2000pp. 456–463
Citations Over TimeTop 1% of 2000 papers
Abstract
We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describing the induction of a probabilistic LTAG model from the Penn Treebank and evaluating its parsing performance. We find that this induction method is an improvement over the EM-based method of (Hwa, 1998), and that the induced model yields results comparable to lexicalized PCFG.
Related Papers
- → A survey of syntactic-semantic parsing based on constituent and dependency structures(2020)35 cited
- Parsing Schemata - a framework for specification and analysis of parsing algorithms(1997)
- → LTAG-spinal and the Treebank(2007)23 cited
- Adapting Multilingual Parsing Models to Sinica Treebank(2012)
- → Parsing Schemata(1993)