Sciweavers

135 search results - page 23 / 27
» A Deductive Approach to Dependency Parsing
Sort
View
EMNLP
2008
13 years 9 months ago
Learning with Probabilistic Features for Improved Pipeline Models
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
Razvan C. Bunescu
EMNLP
2011
12 years 7 months ago
Structured Sparsity in Structured Prediction
Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of ...
André F. T. Martins, Noah A. Smith, M&aacut...
ATAL
2010
Springer
13 years 8 months ago
An integrated possibilistic framework for goal generation in cognitive agents
We propose an integrated theoretical framework, grounded in possibility theory, to account for all the aspects involved in representing and changing beliefs, representing and gene...
Célia da Costa Pereira, Andrea Tettamanzi
GG
2008
Springer
13 years 8 months ago
Pattern-Based Model-to-Model Transformation
We present a new, high-level approach for the specification of model-to-model transformations based on declarative patterns. These are (atomic or composite) constraints on triple ...
Juan de Lara, Esther Guerra
CICLING
2008
Springer
13 years 9 months ago
Semantic and Syntactic Features for Dutch Coreference Resolution
We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolutio...
Iris Hendrickx, Véronique Hoste, Walter Dae...