We show that categories induced by unsupervised word clustering can surpass the performance of gold part-of-speech tags in dependency grammar induction. Unlike classic clustering ...
Valentin I. Spitkovsky, Hiyan Alshawi, Angel X. Ch...
Rank-width is a structural graph measure introduced by Oum and Seymour and aimed at better handling of graphs of bounded clique-width. We propose a formal mathematical framework an...
We describe a bidirectional framework for natural language parsing and generation, using a typedfeatureformalismand an HPSG-based grammar with a parser and generator derived from ...
We address the problem of constructing randomized online algorithms for the Metrical Task Systems (MTS) problem on a metric against an oblivious adversary. Restricting our attenti...
Jacob Abernethy, Peter L. Bartlett, Niv Buchbinder...
In this paper, we provide a study on the use of tree kernels to encode syntactic parsing information in natural language learning. In particular, we propose a new convolution kerne...