Sciweavers

2960 search results - page 376 / 592
» Learning from Multiple Sources
Sort
View
ACL
2008
15 years 5 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
FLAIRS
2006
15 years 5 months ago
Corpus Based Unsupervised Labeling of Documents
Text categorization involves mapping of documents to a fixed set of labels. A similar but equally important problem is that of assigning labels to large corpora. With a deluge of ...
Delip Rao, Deepak P, Deepak Khemani
PSYCHNOLOGY
2006
102views more  PSYCHNOLOGY 2006»
15 years 3 months ago
Radiology Informatics and Work Flow Redesign
The transformation from film-based to filmless operations has become more and more challenging as medical imaging studies expand in size and complexity. To adapt to these changes ...
Guido Vaccari, Carlo Saccavini
CORR
2004
Springer
122views Education» more  CORR 2004»
15 years 3 months ago
Evolution of a Subsumption Architecture Neurocontroller
An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. T...
Julian Togelius
ACL
2010
15 years 1 months ago
Automatic Generation of Story Highlights
In this paper we present a joint content selection and compression model for single-document summarization. The model operates over a phrase-based representation of the source doc...
Kristian Woodsend, Mirella Lapata