12 search results - page 2 / 3 » Deformation-Aware Log-Linear Models |
132
Voted
NAACL
2007
15 years 5 months ago
2007
We propose a novel HMM-based framework to accurately transliterate unseen named entities. The framework leverages features in letteralignment and letter n-gram pairs learned from ...
150
click to vote
NIPS
2003
15 years 5 months ago
2003
Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking f...
135
Voted
NIPS
2007
15 years 5 months ago
2007
We demonstrate that log-linear grammars with latent variables can be practically trained using discriminative methods. Central to efficient discriminative training is a hierarchi...
170
click to vote
EMNLP
2011
14 years 3 months ago
2011
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...