Table 2:

Data statistics of the 3 data setsa

Train Data SetValid Data SetTest Data Set
Non-Definitive585 (30.97%)73 (30.93%)73 (30.8%)
Definitive-Mild329 (17.42%)41 (17.37%)42 (17.7%)
Definitive-Strong503 (26.63%)63 (26.69%)63 (26.58%)
Other472 (24.97%)59 (25%)59 (24.89%)
Total1889 (100%)236 (100%)237 (100%)
  • a Data are the number of sentences and corresponding percentage.