Base | L | % of correct prediction of text fragment sequence | Advantage of NFIM (%) (41) | ||||||||
By unconditional probability | By 1st fragment | By 2nd fragment | By mean probability | Method 1 | Method 2 | Method 3 | Method 4 | Non-force interaction method | |||
“Russian” | 1 | 37.74 | 25.71 | 24.19 | 19.62 | 19.65 | 16.38 | 17.28 | 19.18 | 11.48 | 42.62 |
2 | 21.88 | 14.63 | 14.59 | 11.80 | 11.81 | 11.27 | 10.89 | 11.17 | 8.98 | 21.30 | |
“German” | 1 | 24.10 | 18.11 | 13.11 | 12.47 | 12.99 | 11.61 | 10.85 | 10.70 | 7.60 | 40.85 |
2 | 20.02 | 14.17 | 12.11 | 11.18 | 11.20 | 10.15 | 10.11 | 9.78 | 7.52 | 30.03 | |
“Ukrainian” | 1 | 41.62 | 27.53 | 25.18 | 23.81 | 23.91 | 18.28 | 19.76 | 17.09 | 10.07 | 69.78 |
2 | 3.27 | 2.07 | 2.15 | 1.84 | 1.84 | 1.74 | 1.73 | 1.62 | 1.50 | 8.03 | |
“English” | 1 | 30.99 | 19.32 | 18.52 | 14.78 | 14.87 | 13.40 | 12.43 | 13.02 | 8.74 | 42.21 |
2 | 63.06 | 42.61 | 41.05 | 32.79 | 32.79 | 31.63 | 29.96 | 31.07 | 24.62 | 21.69 |