Table 4 Results of the model that combines word-level and character-level representations (CHARPAIRS -SGNS) and the best performing single component models (CHARPAIRS and SGNS)
From: A deep learning approach to bilingual lexicon induction in the biomedical domain
| Â | Development | |||||
|---|---|---|---|---|---|---|
| Â | Words | Phrases | Words + Phrases | |||
Representation | F1 (top) | F1 (all) | F1 (top) | F1 (all) | F1 (top) | F1 (all) |
CHARPAIRS | 31.95 | 32.32 | 23.70 | 25.97 | 31.39 | 31.92 |
sgns | 23.83 | 26.36 | 17.37 | 17.08 | 25.77 | 25.81 |
CHARPAIRS -SGNS | 34.57 | 33.61 | 18.18 | 23.29 | 33.47 | 32.99 |
| Â | Test | |||||
| Â | Words | Phrases | Words + Phrases | |||
Representation | F1 (top) | F1 (all) | F1 (top) | F1 (all) | F1 (top) | F1 (all) |
CHARPAIRS | 30.70 | 32.19 | 31.82 | 30.61 | 30.81 | 32.15 |
sgns | 22.80 | 24.41 | 26.74 | 27.14 | 23.10 | 24.62 |
CHARPAIRS -SGNS | 34.34 | 34.60 | 23.17 | 26.59 | 33.60 | 34.15 |