Extreme Zero-Shot Learning for Extreme Text Classification

Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit Dhillon


Abstract
The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable to predict unseen labels in dynamic environments, and (2) it requires a large amount of supervised (instance, label) pairs, which can be difficult to obtain for emerging domains. In this paper, we consider a more practical scenario called Extreme Zero-Shot XMC (EZ-XMC), in which no supervision is needed and merely raw text of instances and labels are accessible. Few-Shot XMC (FS-XMC), an extension to EZ-XMC with limited supervision is also investigated. To learn the semantic embeddings of instances and labels with raw text, we propose to pre-train Transformer-based encoders with self-supervised contrastive losses. Specifically, we develop a pre-training method MACLR, which thoroughly leverages the raw text with techniques including Multi-scale Adaptive Clustering, Label Regularization, and self-training with pseudo positive pairs. Experimental results on four public EZ-XMC datasets demonstrate that MACLR achieves superior performance compared to all other leading baseline methods, in particular with approximately 5-10% improvement in precision and recall on average. Moreover, we show that our pre-trained encoder can be further improved on FS-XMC when there are a limited number of ground-truth positive pairs in training. Our code is available at https://github.com/amzn/pecos/tree/mainline/examples/MACLR.
Anthology ID:
2022.naacl-main.399
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5455–5468
Language:
URL:
https://aclanthology.org/2022.naacl-main.399
DOI:
10.18653/v1/2022.naacl-main.399
Bibkey:
Cite (ACL):
Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, and Inderjit Dhillon. 2022. Extreme Zero-Shot Learning for Extreme Text Classification. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5455–5468, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Extreme Zero-Shot Learning for Extreme Text Classification (Xiong et al., NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.naacl-main.399.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2022.naacl-main.399.mp4
Code
 amzn/pecos