Sciweavers

53 search results - page 4 / 11
» Characterizing the Errors of Data-Driven Dependency Parsing ...
Sort
View
ACL
2006
13 years 6 months ago
The Benefit of Stochastic PP Attachment to a Rule-Based Parser
To study PP attachment disambiguation as a benchmark for empirical methods in natural language processing it has often been reduced to a binary decision problem (between verb or n...
Kilian A. Foth, Wolfgang Menzel
ACL
2006
13 years 6 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
ICML
1997
IEEE
14 years 6 months ago
Characterizing the generalization performance of model selection strategies
Abstract: We investigate the structure of model selection problems via the bias/variance decomposition. In particular, we characterize the essential structure of a model selection ...
Dale Schuurmans, Lyle H. Ungar, Dean P. Foster
ICFEM
2007
Springer
13 years 11 months ago
Model Checking with SAT-Based Characterization of ACTL Formulas
Bounded semantics of LTL with existential interpretation and that of ECTL (the existential fragment of CTL), and the characterization of these existentially interpreted properties ...
Wenhui Zhang
NLP
2000
13 years 9 months ago
Monte-Carlo Sampling for NP-Hard Maximization Problems in the Framework of Weighted Parsing
Abstract. The purpose of this paper is (1) to provide a theoretical justification for the use of Monte-Carlo sampling for approximate resolution of NP-hard maximization problems in...
Jean-Cédric Chappelier, Martin Rajman