Sciweavers

EMNLP
2009

Feature-Rich Translation by Quasi-Synchronous Lattice Parsing

13 years 9 months ago
Feature-Rich Translation by Quasi-Synchronous Lattice Parsing
We present a machine translation framework that can incorporate arbitrary features of both input and output sentences. The core of the approach is a novel decoder based on lattice parsing with quasisynchronous grammar (Smith and Eisner, 2006), a syntactic formalism that does not require source and target trees to be isomorphic. Using generic approximate dynamic programming techniques, this decoder can handle "non-local" features. Similar approximate inference techniques support efficient parameter estimation with hidden variables. We use the decoder to conduct controlled experiments on a German-to-English translation task, to compare lexical phrase, syntax, and combined models, and to measure effects of various restrictions on nonisomorphism.
Kevin Gimpel, Noah A. Smith
Added 17 Feb 2011
Updated 17 Feb 2011
Type Journal
Year 2009
Where EMNLP
Authors Kevin Gimpel, Noah A. Smith
Comments (0)