From: A deep learning approach to bilingual lexicon induction in the biomedical domain
 |  | Development | |||||
---|---|---|---|---|---|---|---|
 |  | Words | Phrases | Words + Phrases | |||
Representation | F1 (top) | F1 (all) | F1 (top) | F1 (all) | F1 (top) | F1 (all) | |
sim | bwesg | 13.48 | 9.15 | 21.95 | 15.84 | 14.24 | 9.73 |
 | sgns | 0.55 | 0.88 | NaN | NaN | 0.51 | 0.80 |
class | bwesg | 17.08 | 21.19 | 24.04 | 26.47 | 17.59 | 21.56 |
 | sgns | 23.83 | 25.05 | 25.77 | 27.27 | 23.99 | 25.22 |
 |  | Test | |||||
 |  | Words | Phrases | Words + Phrases | |||
Representation | F1 (top) | F1 (all) | F1 (top) | F1 (all) | F1 (top) | F1 (all) | |
sim | bwesg | 12.78 | 10.03 | 21.43 | 12.52 | 13.52 | 10.31 |
 | sgns | 0.22 | 0.69 | NaN | 0.93 | 0.20 | 0.71 |
class | bwesg | 16.47 | 21.50 | 23.48 | 23.75 | 17.01 | 21.68 |
 | sgns | 22.80 | 24.41 | 26.74 | 27.14 | 23.10 | 24.62 |