On the interaction of automatic evaluation and task framing in headline style transfer

01/05/2021
by   Lorenzo De Mattei, et al.
10

An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based metrics. However, tasks involving subtle textual differences, such as style transfer, tend to be hard for humans to perform. In this paper, we propose an evaluation method for this task based on purposely-trained classifiers, showing that it better reflects system differences than traditional metrics such as BLEU and ROUGE.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset