An efficient implementation of a new DOP model
By Rens Bod. 2003
92 citations recorded by the source corpus.
Two apparently opposing DOP models exist in the literature: one which computes the parse tree involving the most frequent subtrees from a treebank and one which computes the parse tree involving the fewest subtrees from a treebank. This paper proposes an integration of the two models which outperforms each of them separately. Together with a PCFG-reduction of DOP we obtain improved accuracy and efficiency on the Wall Street Journal treebank. Our results show an 11% relative reduction in error rate over previous models, and an average processing time of 3.6 seconds per WSJ sentence.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoav Goldberg
- Mark Steedman
- Stephen Clark
- Luke S. Zettlemoyer
- Laura Rimell
- Noah A. Smith
- James Henderson
- Ivan Titov
Citations in the corpus
- Unbounded Dependency Recovery for Parser Evaluation (2009, background): “Second, it is well known that the accuracy of parsers trained on the Penn Treebank degrades when they are applied to different genres and domains (Gildea, 2001).”
- Discriminative Training of a Neural Network Statistical Parser (2004, methodology): “6% below the current best (Bod, 2003).”
- Productivity and Reuse in Language (2011, unknown): “This estimator assigns equal weight to each training data node (Bod, 2003; J. Goodman, 2003).”
- Forest Reranking: Discriminative Parsing with Non-Local Features (2008, unknown): “G Bod (2003) 90.”
- Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither (2010, background): “(Magerman, 1995; Collins, 1997; Charniak, 2000; Chiang, 2000; Bod, 2003; Charniak and Johnson, 2005; Petrov et al., 2006; Huang, 2008; Finkel et al., 2008; Carreras et al., 2008)).”