32 search results - page 5 / 7 » Training Phrase Translation Models with Leaving-One-Out |
COLING
2008
14 years 11 months ago
2008
Phrasal segmentation models define a mapping from the words of a sentence to sequences of translatable phrases. We discuss the estimation of these models from large quantities of ...
ACL
2007
14 years 11 months ago
2007
Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
EMNLP
2008
14 years 11 months ago
2008
The alignment problem--establishing links between corresponding phrases in two related sentences--is as important in natural language inference (NLI) as it is in machine translati...
113
click to vote
ACL
2011
14 years 1 months ago
2011
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
118
click to vote
TASLP
2008
14 years 9 months ago
2008
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...