Nearest Neighbor Classifier with Margin Penalty for Active Learning
This work addresses the need for improved active learning methods in natural language processing, offering a domain-specific incremental advancement.
The paper tackles the problem of active learning with nearest neighbor classifiers by addressing their inability to ensure inter-class discrepancy, which hinders discovering informative samples in margin areas. The proposed method, NCMAL, adds a margin penalty and a new selection strategy, achieving better results with fewer annotated samples than state-of-the-art baselines in experiments on four datasets.
As deep learning becomes the mainstream in the field of natural language processing, the need for suitable active learning method are becoming unprecedented urgent. Active Learning (AL) methods based on nearest neighbor classifier are proposed and demonstrated superior results. However, existing nearest neighbor classifier are not suitable for classifying mutual exclusive classes because inter-class discrepancy cannot be assured by nearest neighbor classifiers. As a result, informative samples in the margin area can not be discovered and AL performance are damaged. To this end, we propose a novel Nearest neighbor Classifier with Margin penalty for Active Learning(NCMAL). Firstly, mandatory margin penalty are added between classes, therefore both inter-class discrepancy and intra-class compactness are both assured. Secondly, a novel sample selection strategy are proposed to discover informative samples within the margin area. To demonstrate the effectiveness of the methods, we conduct extensive experiments on for datasets with other state-of-the-art methods. The experimental results demonstrate that our method achieves better results with fewer annotated samples than all baseline methods.