We show that plain ROUGE F1 scores are not ideal for comparing current neural systems which on average produce different lengths. This is due to a non-linear pattern between ROUGE F1 and summary length. To alleviate the effect of length during evaluation, we have proposed a new method which normalizes the ROUGE F1 scores of a system by that of a random system with same average output length. A pilot human evaluation has shown that humans prefer short summaries in terms of the verbosity of a summary but overall consider longer summaries to be of higher quality. While human evaluations are more expensive in time and resources, it is clear that normalization, such as the one we proposed for automatic evaluation, will make human evaluations more meaningful.
|Title of host publication||Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation|
|Editors||Thomas Wolf, Hannah Rashkin, Urvashi Khandelwal, Srinivasan Iyer, Marjan Ghazvininejad, Asli Celikyilmaz, Antoine Bosselut|
|Number of pages||9|
|State||Published - 1 Jun 2019|