Sciweavers

564 search results - page 11 / 113
» Training Tree Transducers
Sort
View
ICML
2004
IEEE
14 years 8 months ago
Training conditional random fields via gradient tree boosting
Conditional Random Fields (CRFs; Lafferty, McCallum, & Pereira, 2001) provide a flexible and powerful model for learning to assign labels to elements of sequences in such appl...
Thomas G. Dietterich, Adam Ashenfelter, Yaroslav B...
MT
2007
120views more  MT 2007»
13 years 7 months ago
Capturing practical natural language transformations
We study automata for capturing the transformations in practical natural language processing systems, especially those that translate between human languages. For several variation...
Kevin Knight
IJFCS
2010
60views more  IJFCS 2010»
13 years 6 months ago
Properties of Quasi-Relabeling Tree Bimorphisms
The fundamental properties of the class QUASI of quasi-relabeling relations are investigated. A quasi-relabeling relation is a tree relation that is dened by a tree bimorphism (Ï...
Andreas Maletti, Catalin Ionut Tîrnauca
ACL
2004
13 years 9 months ago
A TAG-based noisy-channel model of speech repairs
This paper describes a noisy channel model of speech repairs, which can identify and correct repairs in speech transcripts. A syntactic parser is used as the source model, and a n...
Mark Johnson, Eugene Charniak
ANLP
1997
81views more  ANLP 1997»
13 years 9 months ago
Name pronunciation in German text-to-speech synthesis
We describe the name analysis and pronunciation component in the German version of the Bell Labs multilingual text-tospeech system. We concentrate on street names because they enc...
Stefanie Jannedy, Bernd Möbius