Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending th...
We discuss existing approaches to train LR parsers, which have been used for statistical resolution of structural ambiguity. These approaches are nonoptimal, in the sense that a c...
We explore the descriptive power, in terms of syntactic phenomena, of a formalism that extends TreeAdjoining Grammar (TAG) by adding a fourth level of hierarchical decomposition t...
Convolution kernels, such as sequence and tree kernels, are advantageous for both the concept and accuracy of many natural language processing (NLP) tasks. Experiments have, howev...
We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for at...