Embedding Hallucination for Few-shot Language Fine-tuning

Yiren Jian, Chongyang Gao, Soroush Vosoughi


Abstract
Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language model can cause severe over-fitting. In this paper, we propose an Embedding Hallucination (EmbedHalluc) method, which generates auxiliary embedding-label pairs to expand the fine-tuning dataset. The hallucinator is trained by playing an adversarial game with the discriminator, such that the hallucinated embedding is indiscriminative to the real ones in the fine-tuning dataset. By training with the extended dataset, the language learner effectively learns from the diverse hallucinated embeddings to overcome the over-fitting issue. Experiments demonstrate that our proposed method is effective in a wide range of language tasks, outperforming current fine-tuning methods. Further, we show that EmbedHalluc outperforms other methods that address this over-fitting problem, such as common data augmentation, semi-supervised pseudo-labeling, and regularization.
Anthology ID:
2022.naacl-main.404
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
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5522–5530
Language:
URL:
https://aclanthology.org/2022.naacl-main.404
DOI:
10.18653/v1/2022.naacl-main.404
Bibkey:
Cite (ACL):
Yiren Jian, Chongyang Gao, and Soroush Vosoughi. 2022. Embedding Hallucination for Few-shot Language Fine-tuning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5522–5530, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Embedding Hallucination for Few-shot Language Fine-tuning (Jian et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.404.pdf
Code
 yiren-jian/embedhalluc
Data
GLUEQNLI