تقرير
Embedding Hallucination for Few-Shot Language Fine-tuning
| العنوان: | Embedding Hallucination for Few-Shot Language Fine-tuning |
|---|---|
| المؤلفون: | Jian, Yiren, Gao, Chongyang, Vosoughi, Soroush |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| الوصف: | 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. Comment: accepted to NAACL 2022 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2205.01307 |
| رقم الأكسشن: | edsarx.2205.01307 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |