Skip to Main Content
Table 2: 
Precision@1 for BLI on the VecMap dataset. The results of MSF-ISF, SL-unsup, CCA-NN (Faruqui and Dyer, 2014), and Adv-Refine are reported by Artetxe et al. (2018b). CCA-NN employs nearest neighbor retrieval procedure. The results of GPA are reported by Kementchedjhieva et al. (2018).
Methoden-iten-deen-fien-esavg.
Supervised      
GeoMM 48.3 49.3 36.1 39.3 43.3 
GeoMMmulti 48.7 49.1 36.0 39.0 43.2 
Procrustes 44.9 46.5 33.5 35.1 40.0 
MSF-ISF 45.3 44.1 32.9 36.6 39.7 
MSF 47.7 47.5 35.4 38.7 42.3 
MSFμ 48.4 47.7 34.7 38.9 42.4 
GPA 45.3 48.5 31.4 − − 
CCA-NN 38.4 37.1 27.6 26.8 32.5 
Unsupervised      
SL-unsup 48.1 48.2 32.6 37.3 41.6 
Adv-Refine 45.2 46.8 0.4 35.4 31.9 
Methoden-iten-deen-fien-esavg.
Supervised      
GeoMM 48.3 49.3 36.1 39.3 43.3 
GeoMMmulti 48.7 49.1 36.0 39.0 43.2 
Procrustes 44.9 46.5 33.5 35.1 40.0 
MSF-ISF 45.3 44.1 32.9 36.6 39.7 
MSF 47.7 47.5 35.4 38.7 42.3 
MSFμ 48.4 47.7 34.7 38.9 42.4 
GPA 45.3 48.5 31.4 − − 
CCA-NN 38.4 37.1 27.6 26.8 32.5 
Unsupervised      
SL-unsup 48.1 48.2 32.6 37.3 41.6 
Adv-Refine 45.2 46.8 0.4 35.4 31.9 
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.
Accept