Embedding Hallucination for Few-Shot Language Fine-tuning
This addresses the problem of over-fitting for researchers and practitioners using few-shot learning with pre-trained language models, though it is an incremental improvement over existing methods.
The paper tackles over-fitting in few-shot language fine-tuning by proposing EmbedHalluc, a method that generates auxiliary embedding-label pairs to expand the dataset, and it outperforms current fine-tuning methods and other over-fitting solutions like data augmentation and regularization.
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. The code will be made available at: https://github.com/yiren-jian/EmbedHalluc.