Hierarchical Attention Prototypical Networks for Few-Shot Text Classification

Shengli Sun, Qingfeng Sun, Kevin Zhou, Tengchao Lv


Abstract
Most of the current effective methods for text classification tasks are based on large-scale labeled data and a great number of parameters, but when the supervised training data are few and difficult to be collected, these models are not available. In this work, we propose a hierarchical attention prototypical networks (HAPN) for few-shot text classification. We design the feature level, word level, and instance level multi cross attention for our model to enhance the expressive ability of semantic space, so it can highlight or weaken the importance of the features, words, and instances separately. We verify the effectiveness of our model on two standard benchmark few-shot text classification datasets—FewRel and CSID, and achieve the state-of-the-art performance. The visualization of hierarchical attention layers illustrates that our model can capture more important features, words, and instances. In addition, our attention mechanism increases support set augmentability and accelerates convergence speed in the training stage.
Anthology ID:
D19-1045
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
476–485
URL:
https://www.aclweb.org/anthology/D19-1045
DOI:
10.18653/v1/D19-1045
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D19-1045.pdf