Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
—The actor programming model offers a promising model for developing reliable parallel and distributed code. Actors provide flexibility and scalability: local execution may be i...
Steven Lauterburg, Mirco Dotta, Darko Marinov, Gul...
Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning an...
We propose a novel dependent hierarchical Pitman-Yor process model for discrete data. An incremental Monte Carlo inference procedure for this model is developed. We show that infe...