Research Article
Biomedical Text Classification Using Augmented Word Representation Based on Distributional and Relational Contexts
Table 2
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 | 0.37086 | 0.02425 | 0.08833 | 0.19136 | −0.12219 | 0.18913 | 0.32734 | 0.08983 | 0.14776 | 0.02051 | 0.12093 | 0.20339 | 0.26537 | 0.17454 | 0.28847 | GloVe_C | 0.37704 | 0.0234 | 0.08882 | 0.19213 | −0.11486 | 0.18979 | 0.32471 | 0.08923 | 0.14850 | 0.02298 | 0.12216 | 0.20214 | 0.26471 | 0.17847 | 0.29069 | GloVe_Merged | 0.38046 | 0.01684 | 0.08901 | 0.19784 | −0.11080 | 0.19142 | 0.32250 | 0.08593 | 0.14683 | 0.02333 | 0.12801 | 0.17483 | 0.26312 | 0.17616 | 0.29588 | WE | 0.38656 | 0.09145 | 0.16012 | 0.19378 | 0.08606 | 0.16619 | 0.36104 | 0.15773 | 0.16101 | 0.23448 | 0.33379 | 0.17740 | 0.28174 | 0.24885 | 0.30282 | CE | 0.3864 | 0.08932 | 0.15778 | 0.19637 | 0.06870 | 0.15468 | 0.36262 | 0.16656 | 0.16486 | 0.25085 | 0.34071 | 0.16746 | 0.28344 | 0.23962 | 0.31748 | Merged | 0.41983 | 0.10333 | 0.17876 | 0.22560 | 0.13349 | 0.16765 | 0.37026 | 0.16420 | 0.15974 | 0.24083 | 0.34355 | 0.19662 | 0.27340 | 0.24228 | 0.29602 |
|
|
Bold means the best performance in the case of each dataset.
|