This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framew...

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framew...

physiographic characteristics and climatic conditions are factors which contributing to river flow regime and understanding of relations between these factors and river flow in a basin result in its application for the ungauged sub-basins river flow prediction. in this research the relation between physiographic and climatic parameters of golestan province and rivers flow were examined by appli...

The artificial dendritic tree, as part of a silicon neuromorph, is modelled as a multibranched, passive cable structure. Synaptic activations are either depolarizing (excitatory), hyperpolarizing (inhibitory), or shunting. Contemporaneous synaptic activation at widely separated sites on the tree result in linear summation of their effects, as do neighboring excitatory and inhibitory activations...

To some extend, many complicated nonlinear maps are additive models of a number of linear and nonlinear terms. A single linear model or nonlinear model (i.e., a neural network model) has its limitation for approximating this class of maps. In this paper, a hybrid approach to evolve an additive tree model for a given problem is proposed. In this approach, tree-structure based evolution algorithm...

A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit the Matrix Tree Theorem (Tutte, 1984) to derive an algorithm that efficiently sums the scores of all nonprojective trees in a sentence, permitting the definition of a conditional log-linear model over trees. While discr...

In this paper, an intelligent controller is applied to control omni-directional robots motion. First, the dynamics of the three wheel robots, as a nonlinear plant with considerable uncertainties, is identified using an efficient algorithm of training, named LoLiMoT. Then, an intelligent controller based on brain emotional learning algorithm is applied to the identified model. This emotional l...

This paper describes the Cunei Machine Translation Platform and how it was used in the WMT ’10 German to English and Czech to English translation tasks. 1 The Cunei Machine Translation Platform The Cunei Machine Translation Platform (Phillips and Brown, 2009) is open-source software and freely available at http://www.cunei. org/. Like Moses (Koehn et al., 2007) and Joshua (Li et al., 2009), Cun...