Wrong output format for evaluation script

[sanxing-chen]

The conlleval.pl script accepts input file format like <span> <groundtruth> <prediction>, but the model's output is <span> <prediction> <groundtruth>. Although it doesn't affect the F1 score, it swaps the values of precision and recall.

[kyzhouhzau]

Yes, you are right thank you for your help for this hidden problem. I will update it.