Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

Timo Schick, Helmut Schmid, Hinrich Schütze


Abstract
A recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained language model and map the predicted words to labels. Manually defining this mapping between words and labels requires both domain expertise and an understanding of the language model’s abilities. To mitigate this issue, we devise an approach that automatically finds such a mapping given small amounts of training data. For a number of tasks, the mapping found by our approach performs almost as well as hand-crafted label-to-word mappings.
Anthology ID:
2020.coling-main.488
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5569–5578
Language:
URL:
https://aclanthology.org/2020.coling-main.488
DOI:
10.18653/v1/2020.coling-main.488
Bibkey:
Cite (ACL):
Timo Schick, Helmut Schmid, and Hinrich Schütze. 2020. Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5569–5578, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (Schick et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2020.coling-main.488.pdf
Code
 timoschick/pet +  additional community code
Data
MultiNLI