Sciweavers

2836 search results - page 69 / 568
» Parsing Algorithms and Metrics
Sort
View
EMNLP
2010
13 years 5 months ago
Top-Down Nearly-Context-Sensitive Parsing
We present a new syntactic parser that works left-to-right and top down, thus maintaining a fully-connected parse tree for a few alternative parse hypotheses. All of the commonly ...
Eugene Charniak
ACL
2006
13 years 9 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
ICDE
1999
IEEE
139views Database» more  ICDE 1999»
14 years 9 months ago
Clustering Large Datasets in Arbitrary Metric Spaces
Clustering partitions a collection of objects into groups called clusters, such that similar objects fall into the same group. Similarity between objects is defined by a distance ...
Venkatesh Ganti, Raghu Ramakrishnan, Johannes Gehr...
CVPR
2009
IEEE
15 years 3 months ago
Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment
In this paper we propose a novel nonparametric approach for object recognition and scene parsing using dense scene alignment. Given an input image, we retrieve its best matches ...
Antonio B. Torralba, Ce Liu, Jenny Yuen
WWW
2004
ACM
14 years 8 months ago
Parsing owl dl: trees or triples?
The Web Ontology Language (OWL) defines three classes of documents: Lite, DL and Full. All RDF/XML documents are OWL Full documents, some OWL Full documents are also OWL DL docume...
Sean Bechhofer, Jeremy J. Carroll