Sciweavers

77 search results - page 8 / 16
» Improved Modeling of Out-Of-Vocabulary Words Using Morpholog...
Sort
View
ICASSP
2011
IEEE
14 years 1 months ago
Multi-class Model M
Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
Ahmad Emami, Stanley F. Chen
NAACL
2003
14 years 11 months ago
Factored Language Models and Generalized Parallel Backoff
We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
Jeff Bilmes, Katrin Kirchhoff
RE
2008
Springer
14 years 9 months ago
Generating Natural Language specifications from UML class diagrams
Early phases of software development are known to be problematic, difficult to manage and errors occurring during these phases are expensive to correct. Many systems have been deve...
Farid Meziane, Nikos Athanasakis, Sophia Ananiadou
IBPRIA
2003
Springer
15 years 2 months ago
Combining Phrase-Based and Template-Based Alignment Models in Statistical Translation
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
Jesús Tomás, Francisco Casacuberta
SIGIR
2005
ACM
15 years 3 months ago
Boosted decision trees for word recognition in handwritten document retrieval
Recognition and retrieval of historical handwritten material is an unsolved problem. We propose a novel approach to recognizing and retrieving handwritten manuscripts, based upon ...
Nicholas R. Howe, Toni M. Rath, R. Manmatha