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
- Editors:
- Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 4604–4609
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.407
- DOI:
- 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)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.coling-1.407.pdf
- Code
- glanceable-io/ordinal-log-loss
- Data
- SNLI, SST, SST-5