The CUED HiFST System for the WMT10 Translation Shared Task

Download: Poster.

The CUED HiFST System for the WMT10 Translation Shared Task” by J. Pino, G. Iglesias, A. Gispert, G. Blackwood, J. Brunning, and W. Byrne. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pp. 155-160 (6 pages).

Abstract

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-risk decoding is an effective framework for multi-source translation, leading to large gains in BLEU score.

Download: Poster.

BibTeX entry:

@inproceedings{wmt2010,
   author = {J. Pino and G. Iglesias and A. Gispert and G. Blackwood and
	J. Brunning and W. Byrne},
   title = {The {CUED} {HiFST} System for the {WMT10} Translation Shared Task},
   booktitle = {Proceedings of the Joint Fifth Workshop on Statistical
	Machine Translation and MetricsMATR},
   pages = {155--160 (6 pages)},
   year = {2010},
   url = {http://www.statmt.org/wmt10/pdf/WMT23.pdf}
}

Back to Bill Byrne publications.