Most state-of-the-art evaluation measures for machine translation assign high costs to movements of word blocks. In many cases though such movements still result in correct or alm...
We present a neural-network-based statistical parser, trained and tested on the Penn Treebank. The neural network is used to estimate the parameters of a generative model of left-...
We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. W...
We propose a novel unsupervised approach for distinguishing literal and non-literal use of idiomatic expressions. Our model combines an unsupervised and a supervised classifier. T...
This work investigates design choices in modeling a discourse scheme for improving opinion polarity classification. For this, two diverse global inference paradigms are used: a su...