Syntactic machine translation systems currently use word alignments to infer syntactic correspondences between the source and target languages. Instead, we propose an unsupervised...
High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from ...
We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs. SCFGs can model equivalence between strings in terms of su...
This paper examines some models of FSMs that can be implemented in dynamically and statically reconfigurable FPGAs. They enable circuits for the FSMs to be constructed in such a wa...
Abstract. This paper presents a method to recover the 3D configuration of a face in each frame of a video. The 3D configuration consists of the three translational parameters and...