We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolutio...
One style of Multi-Engine Machine Translation architecture involves choosing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary s...
Abstract. We present a formalization of lexicalized Recursive Transition Networks which we call Automaton-Based Generative Dependency Grammar (gdg). We show how to extract a gdg fr...
Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven't yet been explored in...
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP withou...