A Simple Log-based Loss Function for Ordinal Text Classification

François Castagnos, Martin Mihelich, Charles Dognin


Abstract
The cross-entropy loss function is widely used and generally considered the default loss function for text classification. When it comes to ordinal text classification where there is an ordinal relationship between labels, the cross-entropy is not optimal as it does not incorporate the ordinal character into its feedback. In this paper, we propose a new simple loss function called ordinal log-loss (OLL). We show that this loss function outperforms state-of-the-art previously introduced losses on four benchmark text classification datasets.
Anthology ID:
2022.coling-1.407
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4604–4609
Language:
URL:
https://aclanthology.org/2022.coling-1.407
DOI:
Bibkey:
Cite (ACL):
François Castagnos, Martin Mihelich, and Charles Dognin. 2022. A Simple Log-based Loss Function for Ordinal Text Classification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4604–4609, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
A Simple Log-based Loss Function for Ordinal Text Classification (Castagnos et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.407.pdf
Code
 glanceable-io/ordinal-log-loss
Data
SNLISST