Created by: tanaka-jp

ERNIE2.0是一篇非常好的论文，令人振奋。 感谢各位作者的努力。

我有一个问题想问一下 关于Sentence Reordering Task，论文中写到， During the pre-training process of this task, a given paragraph is randomly split into 1 to m segments and then all of the combinations are shuffled by a random permuted order. We let the pre-trained model to reorganize these permuted segments, modeled as a k-class classification problem where k= 1! + 2! + 3! + ... + m! .

我的问题是，将一个段落分解为1到m个segment的话， 将被打乱的次序恢复回去，只需要m!种可能性就可以了。 论文中的1! + 2! + 3! + ... + m!的可能性， 是否因为把不相同的segment的个数看作不同情况？