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 ...
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...
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...
Bill MacCartney, Michel Galley, Christopher D. Man...
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...