The CUED HiFST System for the WMT10 Translation Shared Task

  title={The CUED HiFST System for the WMT10 Translation Shared Task},
  author={Juan Pino and Gonzalo Iglesias and Adri{\`a} de Gispert and Graeme W. Blackwood and Jamie Brunning and William J. Byrne},
This paper describes the Cambridge University Engineering Department submission to the Fifth Workshop on Statistical Machine Translation. We report results for the French-English and Spanish-English shared translation tasks in both directions. The CUED system is based on HiFST, a hierarchical phrase-based decoder implemented using weighted finite-state transducers. In the French-English task, we investigate the use of context-dependent alignment models. We also show that lattice minimum Bayes… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 24 references

Spanish Gigaword Second Edition, Linguistic Data Consortium

Angelo Mendonca, David Graff, Denise DiPersio
View 2 Excerpts
Highly Influenced

ficient Path Counting Transducers for Minimum Bayes - Risk Decoding of Statistical Machine Translation Lattices ( to appear )

William Byrne
Proceedings of the ACL • 2010
View 1 Excerpt

Hierarchical phrasebased translation with weighted finite state transducers

Gonzalo Iglesias, Adrià de Gispert, Eduardo R. Banga, William Byrne.
InProceedings of NAACL, pages 433–441. • 2009
View 3 Excerpts

Similar Papers

Loading similar papers…