Closed patrick-wilken closed 1 month ago
Auxiliary metric to check whether the tested system has a general tendency to produce too long / too short hypotheses.
Should be pretty uncontroversial, only design decision is the choice of tokenization. (Even character ratio would be plausible.)
Auxiliary metric to check whether the tested system has a general tendency to produce too long / too short hypotheses.
Should be pretty uncontroversial, only design decision is the choice of tokenization. (Even character ratio would be plausible.)