Output details

Hierarchical phrase-based translation with weighted finite state transducers and shallow-N grammars

The authors have used the methodology described to submit translation systems to internal competitive evaluations of machine translation. The authors had the top-scoring Arabic-English system at the NIST(USA) 2009 Open Machine Translation Evaluation, and were amongst the top French/Spanish-English systems at the 2010 FP-7 sponsored Workshop on Machine Translation. These highly visible results helped secure the EC FP7 FAUST project (EUR2.8M), the US DARPA AGILE (GBP3.5M to Cambridge) and BOLT projects (GBP2M to Cambridge), and a Google Faculty Research Award (USD93K). Iglesias and de Gispert have since joined SDL plc as Research Scientists to help start the Cambridge R&D office.