This paper addresses the task of handling unknown terms in SMT. We propose using source-language monolingual models and resources to paraphrase the source text prior to translatio...
We describe a novel method for the task of unsupervised POS tagging with a dictionary, one that uses integer programming to explicitly search for the smallest model that explains ...
: The LifeWatch Reference Model provides the basis for an interoperable ICT infrastructure for European biodiversity research building on standards whenever feasible. Distinguishin...
We propose several techniques for improving statistical machine translation between closely-related languages with scarce resources. We use character-level translation trained on ...
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...