Ensemble Making Few-Shot Learning Stronger

分类： 计算机科学 >> 计算机科学技术其他学科 提交时间： 2022-11-15

刘永彬

摘要： Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a certain aspect of semantic features, for example, CNN on long-range dependencies part, Transformer on local features. It is difficult for a single model to adapt to various relation learning, which results in a high variance problem. Ensemble strategy could be competitive in improving the accuracy of few-shot relation extraction and mitigating high variance risks. This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features. Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.

通过

 点击量 2137  下载量 325  评论