We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition...
Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven't yet been explored in...
We describe a methodology for rapid experimentation in statistical machine translation which we use to add a large number of features to a baseline system exploiting features from...
Franz Josef Och, Daniel Gildea, Sanjeev Khudanpur,...
In this paper, we propose a linguistically annotated reordering model for BTG-based statistical machine translation. The model incorporates linguistic knowledge to predict orders ...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...