Sciweavers

561 search results - page 80 / 113
» Randomised Language Modelling for Statistical Machine Transl...
Sort
View
COMPUTER
2004
90views more  COMPUTER 2004»
13 years 7 months ago
Languages and the Computing Profession
highly abstracted. The Chinese writing system uses logographs--conventional representations of words or morphemes. Characters of the most common kind have two parts, one suggesting...
W. Neville Holmes
ACTAC
2006
126views more  ACTAC 2006»
13 years 7 months ago
Named Entity Recognition for Hungarian Using Various Machine Learning Algorithms
In this paper we introduce a statistical Named Entity recognizer (NER) system for the Hungarian language. We examined three methods for identifying and disambiguating proper nouns...
Richárd Farkas, György Szarvas, Andr&a...
ICML
2008
IEEE
14 years 8 months ago
Structure compilation: trading structure for features
Structured models often achieve excellent performance but can be slow at test time. We investigate structure compilation, where we replace structure with features, which are often...
Dan Klein, Hal Daumé III, Percy Liang
COLING
2010
13 years 2 months ago
An Empirical Study on Web Mining of Parallel Data
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
Gum-Won Hong, Chi-Ho Li, Ming Zhou, Hae-Chang Rim
NAACL
2010
13 years 5 months ago
Unsupervised Syntactic Alignment with Inversion Transduction Grammars
Syntactic machine translation systems currently use word alignments to infer syntactic correspondences between the source and target languages. Instead, we propose an unsupervised...
Adam Pauls, Dan Klein, David Chiang, Kevin Knight