Knowledge-Aware Meta-learning for Low-Resource Text Classification
This work addresses low-resource text classification for NLP applications, presenting an incremental improvement by incorporating knowledge graphs into meta-learning.
The paper tackles the problem of low-resource text classification by bridging the gap between meta-training and meta-testing tasks using external knowledge bases, resulting in effective performance demonstrated through extensive experiments on three datasets.
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms, may not generalize well to testing tasks when they are not well-supported by training tasks. This paper studies a low-resource text classification problem and bridges the gap between meta-training and meta-testing tasks by leveraging the external knowledge bases. Specifically, we propose KGML to introduce additional representation for each sentence learned from the extracted sentence-specific knowledge graph. The extensive experiments on three datasets demonstrate the effectiveness of KGML under both supervised adaptation and unsupervised adaptation settings.