Maybe an error in the original paper?

[ThomasjonLi]

In the paper, the calculation of IRR loss made me confused,

We can treat this as an CE loss. |M| can be treat as the batch size, |V| can be treat as the class num. As $y^i$ is one-hot,so only single $y^i_j$ is set to 1 and others are 0. Thus the loss should not be divided by |V|.

[mikanatsumi]

This is not an error. In the code itself they have used simple CE loss by pytorch. They have just written it like this intentionally.