In this work we address the problem of managing interconnect timing in high-level synthesis by generating a layoutfriendly microarchitecture. A metric called spreading score is pr...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeli...
Motivation: Next-generation sequencing methods are generating increasingly massive datasets, yet still do not fully capture genetic diversity in the richest environments. To under...
Alex L. B. Leach, James P. J. Chong, Kelly R. Rede...