We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue ...
String-to-string transduction is a central problem in computational linguistics and natural language processing. It occurs in tasks as diverse as name transliteration, spelling co...
Approximate MAP inference in graphical models is an important and challenging problem for many domains including computer vision, computational biology and natural language unders...
The end-to-end performance of natural language processing systems for compound tasks, such as question answering and textual entailment, is often hampered by use of a greedy 1-bes...
Jenny Rose Finkel, Christopher D. Manning, Andrew ...