Skip to Main Content
Table 12 
Analysis of symmetric re-weighting–based refinement applied to the same initial mappings of our adversarial autoencoder on the Dinu-Artetxe data set.
 En-EsEn-ItEn-DeEn-Fi
Symmetric re-weighting 46.5 42.4 37.5 31.9 48.3 44.1 32.4 32.7 
OLS 41.8 36.7 29.0 29.6 41.5 39.3 27.7 26.9 
OLS + Orthogonality 45.1 39.5 35.7 31.7 47.6 43.8 30.9 32.3 
OLS with L1 regularizer (LASSO) 42.3 36.9 28.4 30.4 42.3 39.7 26.8 27.1 
LASSO + Orthogonality 46.0 40.1 34.8 32.2 47.1 44.2 32.4 32.6 
OLS with L2 regularizer (RIDGE) 41.7 36.5 29.4 29.5 41.9 39.0 28.2 29.4 
RIDGE + Orthogonality 46.2 39.9 35.1 32.0 47.8 44.2 32.7 32.7 
OLS with L1 & L2 regularizers (E-NET) 42.1 36.8 29.3 30.1 42.2 38.2 28.5 28.5 
E-NET + Orthogonality 45.6 40.3 35.3 31.6 47.7 44.0 32.5 32.9 
 En-EsEn-ItEn-DeEn-Fi
Symmetric re-weighting 46.5 42.4 37.5 31.9 48.3 44.1 32.4 32.7 
OLS 41.8 36.7 29.0 29.6 41.5 39.3 27.7 26.9 
OLS + Orthogonality 45.1 39.5 35.7 31.7 47.6 43.8 30.9 32.3 
OLS with L1 regularizer (LASSO) 42.3 36.9 28.4 30.4 42.3 39.7 26.8 27.1 
LASSO + Orthogonality 46.0 40.1 34.8 32.2 47.1 44.2 32.4 32.6 
OLS with L2 regularizer (RIDGE) 41.7 36.5 29.4 29.5 41.9 39.0 28.2 29.4 
RIDGE + Orthogonality 46.2 39.9 35.1 32.0 47.8 44.2 32.7 32.7 
OLS with L1 & L2 regularizers (E-NET) 42.1 36.8 29.3 30.1 42.2 38.2 28.5 28.5 
E-NET + Orthogonality 45.6 40.3 35.3 31.6 47.7 44.0 32.5 32.9 
Close Modal

or Create an Account

Close Modal
Close Modal