Sciweavers

896 search results - page 138 / 180
» A Compiler Approach to Performance Prediction Using Empirica...
Sort
View
EMNLP
2008
13 years 10 months ago
Stacking Dependency Parsers
We explore a stacked framework for learning to predict dependency structures for natural language sentences. A typical approach in graph-based dependency parsing has been to assum...
André F. T. Martins, Dipanjan Das, Noah A. ...
JMLR
2012
11 years 11 months ago
On Nonparametric Guidance for Learning Autoencoder Representations
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
KDD
2007
ACM
190views Data Mining» more  KDD 2007»
14 years 9 months ago
Model-shared subspace boosting for multi-label classification
Typical approaches to multi-label classification problem require learning an independent classifier for every label from all the examples and features. This can become a computati...
Rong Yan, Jelena Tesic, John R. Smith
JAIR
2006
137views more  JAIR 2006»
13 years 8 months ago
Learning Sentence-internal Temporal Relations
In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either e...
Maria Lapata, Alex Lascarides
PERCOM
2008
ACM
14 years 8 months ago
Information Agents for Pervasive Sensor Networks
In this paper, we describe an information agent, that resides on a mobile computer or personal digital assistant (PDA), that can autonomously acquire sensor readings from pervasiv...
Alex Rogers, Mike Osborne, Sarvapali D. Ramchurn, ...