Resource title

Dependency-based machine translation and parallel parsing without the projectivity and edge-factoring assumptions - A white paper

Resource image

image for OpenScout resource :: Dependency-based machine translation and parallel parsing without the projectivity and edge-factoring assumptions - A white paper

Resource description

In this white paper, we review the theoretical evidence about the computational efficiency of dependency parsing and machine translation without the widely used, but linguistically questionable assumptions about projectivity and edge-factoring. On the basis of the heuristic local optimality parser proposed by (Buch-Kromann, 2006), we propose a common architecture for monolingual parsing, parallel parsing, and translation that does not make these assumptions. Finally, we describe the elementary repair operations in the model, and argue that the model is potentially interesting as a model of human translation.

Resource author

Matthias Buch-Kromann

Resource publisher

Resource publish date

Resource language

eng

Resource content type

application/pdf

Resource resource URL

http://hdl.handle.net/10398/6846

Resource license

Check the according license before adaptation. When adapting give credits to the original author.