EMNLP
2009
13 years 9 months ago
2009
Virtual evidence (VE), first introduced by (Pearl, 1988), provides a convenient way of incorporating prior knowledge into Bayesian networks. This work generalizes the use of VE to...
EMNLP
2009
13 years 9 months ago
2009
EMNLP
2009
13 years 9 months ago
2009
Bilingual dictionaries are vital resources in many areas of natural language processing. Numerous methods of machine translation require bilingual dictionaries with large coverage...
EMNLP
2009
13 years 9 months ago
2009
Semantic Role Labeling (SRL) has proved to be a valuable tool for performing automatic analysis of natural language texts. Currently however, most systems rely on a large training...
EMNLP
2009
13 years 9 months ago
2009
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm. The res...
EMNLP
2009
13 years 9 months ago
2009
We propose a novel language-independent approach for improving statistical machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. Mo...
EMNLP
2009
13 years 9 months ago
2009
A large body of recent research has been investigating the acquisition and application of applied inference knowledge. Such knowledge may be typically captured as entailment rules...
EMNLP
2009
13 years 9 months ago
2009
We present a method to align words in a bitext that combines elements of a traditional statistical approach with linguistic knowledge. We demonstrate this approach for Arabic-Engl...
EMNLP
2009
13 years 9 months ago
2009
Set expansion refers to expanding a partial set of "seed" objects into a more complete set. One system that does set expansion is SEAL (Set Expander for Any Language), w...
EMNLP
2009
13 years 9 months ago
2009
This paper proposes a method that speeds up a classifier trained with many conjunctive features: combinations of (primitive) features. The key idea is to precompute as partial res...