Abstract
We present one of the preliminary NLP works under the challenging setup of Learning from Label Proportions (LLP), where the data is provided in an aggregate form called bags and only the proportion of samples in each class as the ground truth. This setup is inline with the desired characteristics of training models under Privacy settings and Weakly supervision. By characterizing some irregularities of the most widely used baseline technique DLLP, we propose a novel formulation that is also robust. This is accompanied with a learnability result that provides a generalization bound under LLP. Combining this formulation with a self-supervised objective, our method achieves better results as compared to the baselines in almost 87% of the experimental configurations which include large scale models for both long and short range texts across multiple metrics.- Anthology ID:
- 2023.findings-emnlp.817
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12210–12223
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.817
- DOI:
- 10.18653/v1/2023.findings-emnlp.817
- Cite (ACL):
- Jatin Chauhan, Xiaoxuan Wang, and Wei Wang. 2023. Learning under Label Proportions for Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12210–12223, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Learning under Label Proportions for Text Classification (Chauhan et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ijclclp-past-ingestion/2023.findings-emnlp.817.pdf