In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems....
Given multiple translations of the same source sentence, how to combine them to produce a translation that is better than any single system output? We propose a hierarchical syste...
We propose a domain specific model for statistical machine translation. It is wellknown that domain specific language models perform well in automatic speech recognition. We show ...
Several solutions have been proposed to exploit the availability of heterogeneous sources of biomolecular data for gene function prediction, but few attention has been dedicated t...