Sciweavers

Share
ICASSP
2010
IEEE

Hypothesis ranking and two-pass approaches for machine translation system combination

9 years 10 months ago
Hypothesis ranking and two-pass approaches for machine translation system combination
Given a number of machine translations of a source segment, the goal of system combination is to produce a new translation that has better quality than all of them. This paper describes a number of improvements that were recently added to the JHU system combination scheme: (i) A hypothesis ranking technique which orders the system outputs, on a per-segment basis, according to predicted translation quality, thus improving a subsequent incremental combination step. (ii) A two-pass combination procedure, which first produces several combination outputs with the given translations, and then performs one more combination step with these new outputs. Results from the NIST MT09 informal system combination evaluation on Arabic-to-English and Urdu-to-English1 show that both approaches offer significant BLEU and TER gains over a baseline JHU combination scheme.
Damianos Karakos, Jason Smith, Sanjeev Khudanpur
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Damianos Karakos, Jason Smith, Sanjeev Khudanpur
Comments (0)
books