Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar

Open Access
Authors
Publication date 2011
Host editors
  • D. Seddah
  • R. Tsarfaty
  • J. Foster
Book title The Second Workshop on Statistical Parsing of Morphologically-Rich Languages (SPMRL 2011)
Book subtitle IWPT 2011 : proceedings of SPMRL 2011 : October 6, 2011, Dublin, Ireland
ISBN (electronic)
  • 9781932432732
Event 2nd Workshop on Statistical Parsing of Morphologically-Rich Languages
Pages (from-to) 34-44
Publisher Stroudsburg, PA: The Association for Computational Linguistics
Organisations
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Abstract Recent advances in parsing technology have made treebank parsing with discontinuous constituents possible, with parser output of competitive quality (Kallmeyer and Maier, 2010). We apply Data-Oriented Parsing (DOP) to a grammar formalism that allows for discontinuous trees (LCFRS). Decisions during parsing are conditioned on all possible fragments, resulting in improved performance. Despite the fact that both DOP and discontinuity present formidable challenges in terms of computational complexity, the model is reasonably efficient, and surpasses the state of the art in discontinuous parsing.
Document type Conference contribution
Language English
Published at http://aclweb.org/anthology/W11-3805
Downloads
W11-3805 (Final published version)
Permalink to this page
Back