Statistical Machine Translation - overview
User Experience Accomplishment | 2009
IBM researcher: Salim Roukos
Where the work was done: IBM T.J. Watson Research Center
What we accomplished: Roukos (pictured) helped revolutionize the field of statistical machine translation by casting the problem as a statistical communication model rather than the more traditional approach of rule-based systems. The key challenges involved the development of a series of steps to estimate more complex translation models from earlier easier and cruder translation models. A sequence of five models was used to estimate a word alignment between the words of a source and a target sentence. These models are referred to in the scientific literature as "IBM Model through IBM Model 5."
Related links: Wikipedia entry; Systems Combination for Machine Translation of Spoken and Written Language; A Maximum Entropy World Aligner for Arabic-English Machine Translation
BACK TO IBM RESEARCH ACCOMPLISHMENTS
Image credit: IBM