479 search results - page 16 / 96 » Statistical Significance Tests for Machine Translation Evalu... |
134
click to vote
ACL
2010
14 years 12 months ago
2010
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech r...
101
click to vote
EMNLP
2009
14 years 11 months ago
2009
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...
127
click to vote
EMNLP
2009
14 years 11 months ago
2009
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
112
click to vote
ACL
2009
14 years 11 months ago
2009
The tree sequence based translation model allows the violation of syntactic boundaries in a rule to capture non-syntactic phrases, where a tree sequence is a contiguous sequence o...
117
click to vote
ACL
2009
14 years 11 months ago
2009
Statistical machine translation (SMT) models require bilingual corpora for training, and these corpora are often multilingual with parallel text in multiple languages simultaneous...