MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification
This work addresses the problem of text classification with very few labeled examples per class, which is crucial for applications with limited data, though it is an incremental improvement over existing metric-based meta-learning methods.
The paper tackles few-shot text classification by proposing a meta-learning method that performs instance-wise comparison and aggregation to generate class-wise matching vectors, avoiding the need for compact prototype representations. It significantly outperforms existing state-of-the-art approaches in both standard and generalized few-shot learning settings.
Text classification struggles to generalize to unseen classes with very few labeled text instances per class. In such a few-shot learning (FSL) setting, metric-based meta-learning approaches have shown promising results. Previous studies mainly aim to derive a prototype representation for each class. However, they neglect that it is challenging-yet-unnecessary to construct a compact representation which expresses the entire meaning for each class. They also ignore the importance to capture the inter-dependency between query and the support set for few-shot text classification. To deal with these issues, we propose a meta-learning based method MGIMN which performs instance-wise comparison followed by aggregation to generate class-wise matching vectors instead of prototype learning. The key of instance-wise comparison is the interactive matching within the class-specific context and episode-specific context. Extensive experiments demonstrate that the proposed method significantly outperforms the existing state-of-the-art approaches, under both the standard FSL and generalized FSL settings.