This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
The development of technologies to address machine translation and distillation of multilingual broadcast data depends heavily on the collection of large volumes of material from ...
We describe the Arabic broadcast transcription system elded by IBM in the GALE Phase 4 machine translation evaluation. Key advances over our Phase 3.5 system include improvements ...
Brian Kingsbury, Hagen Soltau, George Saon, Stephe...
Abstract--This paper presents a model for machine aided human translation (MAHT) that integrates source language text and target language acoustic information to produce the text t...