Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
In statistical language modeling, one technique to reduce the problematic effects of data sparsity is to partition the vocabulary into equivalence classes. In this paper we invest...
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently....
An ideal summarization system should produce summaries that have high content coverage and linguistic quality. Many state-ofthe-art summarization systems focus on content coverage...
We present a hierarchical phrase-based statistical machine translation in which a target sentence is efficiently generated in left-to-right order. The model is a class of synchron...