Abstract: 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 SOTA approaches, under both the standard FSL and generalized FSL settings.
Paper Link: https://openreview.net/forum?id=6rSRL11c365
Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)
Presentation Mode: This paper will be presented virtually
Virtual Presentation Timezone: UTC-8
Copyright Consent Signature (type Name Or NA If Not Transferrable): Jianhai Zhang
Copyright Consent Name And Address: Alibaba Group, No. 969, Wenyi West Road, Yuhang District, Hangzhou, China