Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
This paper introduces a system that automatically classifies registration problems based on the type of registration required. Rather than rely on a single "best" algorit...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...
In this paper, an improved approach to blind deconvolution of LTI systems incorporating phase unwrapping is presented. The method can recover a noise-free estimate of the logarith...
We propose two methods for finding similarities in protein structure databases. Our techniques extract feature vectors on triplets of SSEs (Secondary Structure Elements) of prote...