Papers with -shot training
On Training Instance Selection for Few-Shot Neural Text Generation (2021.acl-short)
Copied to clipboard
| Challenge: | Pretraining large neural networks with a language modeling objective has led to dramatic improvements in text generation. |
| Approach: | They propose a selection strategy to select few-shot training instances based on unlabeled data to identify the most worthwhile data points that should be annotated under some budget of labeling cost. |
| Outcome: | The proposed strategy outperforms random sampling on three text generation tasks. |
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for prompt tuning can overfit to few-shot training samples, causing overfitting . authors propose a new framework for prompt learning with supervised meta-learning . |
| Approach: | They propose a self-supervised meta-prompt learning framework with MEta-gradient Regularization for few-shot generalization that leverages self-recognized meta-learning with a diverse set of meta-tasks to learn a universal prompt initialization using only unlabeled data. |
| Outcome: | The proposed framework learns a universal prompt initialization for efficient adaptation using only unlabeled data. |
Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Widely used multi-modal pretrained models generalize poorly to out-of-distribution data, suggesting shortcomings in the VLE2E pipeline. |
| Approach: | They develop a segment-combine test for multi-image queries and contrast set for cross-benchmark transfer. |
| Outcome: | The proposed method shows that it is possible to train both neural and neuro-symbolic models in the same way. |