Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification

Yookyung Kho, Jaehee Kim, Pilsung Kang


Abstract
Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task. This approach reformulates the fine-tuning objective to align with the Masked Language Modeling (MLM) objective. Leveraging unlabeled data, prompt-based self-training has shown greater effectiveness in binary and three-class classification. However, prompt-based self-training for multi-class classification has not been adequately investigated, despite its significant applicability to real-world scenarios. Moreover, extending current methods to multi-class classification suffers from the verbalizer that extracts the predicted value of manually pre-defined single label word for each class from MLM predictions. Consequently, we introduce a novel, efficient verbalizer structure, named Mapping-free Automatic Verbalizer (MAV). Comprising two fully connected layers, MAV serves as a trainable verbalizer that automatically extracts the requisite word features for classification by capitalizing on all available information from MLM predictions. Experimental results on five multi-class classification datasets indicate MAV’s superior self-training efficacy.
Anthology ID:
2023.findings-emnlp.921
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:
13786–13800
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.921
DOI:
10.18653/v1/2023.findings-emnlp.921
Bibkey:
Cite (ACL):
Yookyung Kho, Jaehee Kim, and Pilsung Kang. 2023. Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13786–13800, Singapore. Association for Computational Linguistics.
Cite (Informal):
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification (Kho et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.921.pdf