Research Article
Biomedical Text Classification Using Augmented Word Representation Based on Distributional and Relational Contexts
Table 4
Word similarity performance with
and
.
| Word embeddings | BioSimLex | BioSimVerb | MEN | MTurk | RG65 | RW | SCWS | SimLex999 | TR9856 | UMNSRS-rel | UMNSRS-sim | VERB143 | WS353 | WS353R | WS353S |
| GloVe_W | 0.41447 | 0.03500 | 0.11218 | 0.25121 | −0.08405 | 0.19361 | 0.34490 | 0.10936 | 0.14681 | 0.08276 | 0.16010 | 0.25775 | 0.23949 | 0.15827 | 0.27814 | GloVe_C | 0.40711 | 0.034104 | 0.11319 | 0.25104 | −0.07161 | 0.19433 | 0.34930 | 0.10657 | 0.14861 | 0.08063 | 0.15738 | 0.24971 | 0.24406 | 0.1695 | 0.27649 | GloVe_Merged | 0.42232 | 0.03079 | 0.11085 | 0.24424 | −0.07091 | 0.19534 | 0.34576 | 0.10382 | 0.14725 | 0.08224 | 0.16911 | 0.23834 | 0.24284 | 0.16355 | 0.29231 | WE | 0.43159 | 0.13004 | 0.19873 | 0.28795 | 0.13609 | 0.21529 | 0.37697 | 0.15218 | 0.15606 | 0.25885 | 0.33819 | 0.28255 | 0.34254 | 0.27483 | 0.40136 | CE | 0.45262 | 0.13312 | 0.20081 | 0.28509 | 0.18909 | 0.17872 | 0.37275 | 0.15449 | 0.15126 | 0.22989 | 0.32402 | 0.28431 | 0.34823 | 0.31235 | 0.40330 | Merged | 0.43254 | 0.17497 | 0.21834 | 0.27677 | 0.22149 | 0.13459 | 0.37611 | 0.15299 | 0.15817 | 0.28289 | 0.35350 | 0.18635 | 0.28867 | 0.25955 | 0.32509 |
|
|
Bold means the best performance in the case of each dataset.
|