Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training. More p...
We introduce a stochastic grammatical channel model for machine translation, that synthesizes several desirable characteristics of both statistical and grammatical machine transla...
Background: Genetic recombination can produce heterogeneous phylogenetic histories within a set of homologous genes. These recombination events can be obscured by subsequent resid...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...
Background: Probabilistic models for sequence comparison (such as hidden Markov models and pair hidden Markov models for proteins and mRNAs, or their context-free grammar counterp...