Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data

Dheeraj Mekala, Varun Gangal, Jingbo Shang


Abstract
Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned fine-tuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.
Anthology ID:
2021.emnlp-main.46
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
583–594
Language:
URL:
https://aclanthology.org/2021.emnlp-main.46
DOI:
10.18653/v1/2021.emnlp-main.46
Bibkey:
Cite (ACL):
Dheeraj Mekala, Varun Gangal, and Jingbo Shang. 2021. Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 583–594, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data (Mekala et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.46.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.46.mp4