We present a phrasal synchronous grammar model of translational equivalence. Unlike previous approaches, we do not resort to heuristics or constraints from a word-alignment model,...
Phil Blunsom, Trevor Cohn, Chris Dyer, Miles Osbor...
Features derived from Multi-Layer Perceptrons (MLPs) are becoming increasingly popular for speech recognition. This paper describes various schemes for applying these features to ...
J. Park, Frank Diehl, M. J. F. Gales, Marcus Tomal...
Kahn Process Networks (KPN) are an appealing model of computation to specify streaming applications. When a KPN has to execute on a multi-processor platform, a mapping of the KPN m...
Process modelling systems are complex and difficult to compare. A key attribute of any process modelling formalism or tool is time which involves how it handles and represents tem...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...