A language model uses the following formula to calculate the probability of a specific word j, which belongs to partition u from a set of n_u partitions of the vocabulary:

α_{i,j} = \frac{\exp(\beta_{i,j})}{\sum_{\mathbf{k}_{j'} \in \mathbf{K}^{[1]}} \exp(\beta_{i,j'}) + \cdots + \sum_{\mathbf{k}_{j'} \in \mathbf{K}^{[u]}} \exp(\beta_{i,j'}) + \cdots + \sum_{\mathbf{k}_{j'} \in \mathbf{K}^{[n_u]}} \exp(\beta_{i,j'})}

Based on the structure of this formula, what is a key characteristic