IndexBrowse   BibliographiesMy selection
 Search: in   (word length ≥ 3)
Reference no #691   Download bibtex file Type :   Html | Bib | Both
    Created: 2007-12-12 11:30:33
691 Add to my selection
      AUTHOR = {Kiefer, Bernd and Krieger, Hans-Ulrich and Prescher, Detlef},
      TITLE = {A Novel Disambiguation Method For Unification-Based Grammars Using Probabilistic Context-Free Approximations},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics (COLING'02), August 24 - September 1},
      ADDRESS = {Taipei, Taiwan},
      URL = {},
      ABSTRACT = {We present a novel disambiguation method for unificationbased grammars (UBGs). In contrast to other methods, our approach obviates the need for probability models on the UBG side in that it shifts the responsibility to simpler contextfree models, indirectly obtained from the UBG. Our approach has three advantages: (i) training can be effectively done in practice, (ii) parsing and disambiguation of contextfree readings requires only cubic time, and (iii) involved probability distributions are mathematically clean. In an experiment for a midsize UBG, we show that our novel approach is feasible. Using unsupervised training, we achieve 88% accuracy on an exactmatch task.},
      ANNOTE = {COLIURL : Kiefer:2002:NDM.pdf}
Last modified: Thu October 16 2014 19:11:34         BibAdmin