Research Article
Biomedical Text Classification Using Augmented Word Representation Based on Distributional and Relational Contexts
Table 5
Word similarity performance with
and
.
| Word embeddingss | BioSimLex | BioSimVerb | MEN | MTurk | RG65 | RW | SCWS | SimLex999 | TR9856 | UMNSRS-rel | UMNSRS-sim | VERB143 | WS353 | WS353R | WS353S |
| GloVe_W | 0.43207 | 0.02696 | 0.10992 | 0.25905 | −0.08043 | 0.19756 | 0.33868 | 0.10524 | 0.14693 | 0.07269 | 0.14784 | 0.25767 | 0.23913 | 0.15315 | 0.27493 | GloVe_C | 0.43398 | 0.02142 | 0.11191 | 0.26266 | −0.07475 | 0.19811 | 0.3446 | 0.10384 | 0.14785 | 0.08083 | 0.15536 | 0.25638 | 0.23976 | 0.15199 | 0.27944 | GloVe_M erged | 0.44134 | 0.02201 | 0.11245 | 0.25225 | −0.07852 | 0.19850 | 0.34179 | 0.09961 | 0.14727 | 0.08368 | 0.16740 | 0.23064 | 0.23776 | 0.15446 | 0.28936 | WE | 0.47840 | 0.13275 | 0.20673 | 0.25842 | 0.18457 | 0.17788 | 0.38499 | 0.16691 | 0.15209 | 0.22026 | 0.32647 | 0.29077 | 0.34063 | 0.28352 | 0.40837 | CE | 0.46382 | 0.13086 | 0.20928 | 0.26134 | 0.16582 | 0.21132 | 0.38783 | 0.16750 | 0.15691 | 0.24632 | 0.32926 | 0.29349 | 0.33343 | 0.24460 | 0.40477 | Merged | 0.46763 | 0.17310 | 0.23866 | 0.26765 | 0.21509 | 0.13608 | 0.38736 | 0.16625 | 0.16164 | 0.27901 | 0.35348 | 0.18967 | 0.29661 | 0.25495 | 0.34478 |
|
|
Bold means the best performance in the case of each dataset.
|