TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
This work improves few-shot text classification for NLP applications, offering a novel method to handle classes with similar semantics, though it is incremental within meta-learning.
The paper tackles the problem of few-shot text classification by addressing performance dependence on inter-class variance, proposing TART to transform class prototypes into task-adaptive metric spaces, resulting in surpassing state-of-the-art methods by up to 7.4% on benchmark datasets.
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.