ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification

Kaihao Guo, Hang Yu, Cong Liao, Jianguo Li, Haipeng Zhang


Abstract
Many text classification tasks require handling unseen domains with plenty of unlabeled data, thus giving rise to the self-adaption or the so-called transductive zero-shot learning (TZSL) problem. However, current methods based solely on encoders or decoders overlook the possibility that these two modules may promote each other. As a first effort to bridge this gap, we propose an autoencoder named ZeroAE. Specifically, the text is encoded with two separate BERT-based encoders into two disentangled spaces, i.e., label-relevant (for classification) and label-irrelevant respectively. The two latent spaces are then decoded by prompting GPT-2 to recover the text as well as to further generate text with labels in the unseen domains to train the encoder in turn. To better exploit the unlabeled data, a novel indirect uncertainty-aware sampling (IUAS) approach is proposed to train ZeroAE. Extensive experiments show that ZeroAE largely surpasses the SOTA methods by 15.93% and 8.70% on average respectively in the label-partially-unseen and label-fully-unseen scenario. Notably, the label-fully-unseen ZeroAE even possesses superior performance to the label-partially-unseen SOTA methods.
Anthology ID:
2023.findings-acl.200
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3202–3219
Language:
URL:
https://aclanthology.org/2023.findings-acl.200
DOI:
10.18653/v1/2023.findings-acl.200
Bibkey:
Cite (ACL):
Kaihao Guo, Hang Yu, Cong Liao, Jianguo Li, and Haipeng Zhang. 2023. ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3202–3219, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification (Guo et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-acl.200.pdf