Devil’s Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification
Abstract
We present a new form of ensemble method–Devil’s Advocate, which uses a deliberately dissenting model to force other submodels within the ensemble to better collaborate. Our method consists of two different training settings: one follows the conventional training process (Norm), and the other is trained by artificially generated labels (DevAdv). After training the models, Norm models are fine-tuned through an additional loss function, which uses the DevAdv model as a constraint. In making a final decision, the proposed ensemble model sums the scores of Norm models and then subtracts the score of the DevAdv model. The DevAdv model improves the overall performance of the other models within the ensemble. In addition to our ensemble framework being based on psychological background, it also shows comparable or improved performance on 5 text classification tasks when compared to conventional ensemble methods.- Anthology ID:
- 2021.findings-emnlp.187
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2168–2174
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.187
- DOI:
- 10.18653/v1/2021.findings-emnlp.187
- Cite (ACL):
- Hwiyeol Jo, Jaeseo Lim, and Byoung-Tak Zhang. 2021. Devil’s Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2168–2174, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Devil’s Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification (Jo et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.findings-emnlp.187.pdf
- Code
- hwiyeoljo/devilsadvocate
- Data
- AG News, IMDb Movie Reviews