Table 5: 
BLEU scores for weakly supervised MT experiments. Boldfaced results are significantly better than the baseline at p < 0.05 according to multeval (Clark et al., 2011). * marks a significant difference over RAMP−.
M% BLEUΔ
1 MLE 64 15.59  
2 RAMP 40 15.03 ± 0.01 −0.56 
3 RAMP1− 40 15.12 ± 0.02 − 0.47 
4 RAMP2 40 15.19 ± 0.01 − 0.40 
5 MRTδ1 1 15.37 ± 0.04 − 0.22 
6 MRTδ2 1 15.70 ± 0.04  + 0.11 
7 RAMP− 40 15.85 ± 0.02  + 0.26 
8 RAMPδ2 40 15.86 ± 0.04  + 0.27 
9 RAMP−-T 40 16.03*± 0.02  + 0.44 
10 RAMPδ2-T 40 15.84 ± 0.02  + 0.25 
M% BLEUΔ
1 MLE 64 15.59  
2 RAMP 40 15.03 ± 0.01 −0.56 
3 RAMP1− 40 15.12 ± 0.02 − 0.47 
4 RAMP2 40 15.19 ± 0.01 − 0.40 
5 MRTδ1 1 15.37 ± 0.04 − 0.22 
6 MRTδ2 1 15.70 ± 0.04  + 0.11 
7 RAMP− 40 15.85 ± 0.02  + 0.26 
8 RAMPδ2 40 15.86 ± 0.04  + 0.27 
9 RAMP−-T 40 16.03*± 0.02  + 0.44 
10 RAMPδ2-T 40 15.84 ± 0.02  + 0.25 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept