Diverse Few-Shot Text Classification with Multiple Metrics

Abstract

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting, where tasks are diverse. However, it imposes tremendous difficulties to existing state-of-the-art metric-based algorithms since a single metric is insufficient to capture complex task variations in natural language domain. To alleviate the problem, we propose an adaptive metric learning approach that automatically determines the best weighted combination from a set of metrics obtained from meta-training tasks for a newly seen few-shot task. Extensive quantitative evaluations on real-world sentiment analysis and dialog intent classification datasets demonstrate that the proposed method performs favorably against state-of-the-art few shot learning algorithms in terms of predictive accuracy. We make our code and data available for further study.

arXiv commentNAACL 2018. 11+5 pages. arXiv admin note: text overlap with arXiv:1708.07918

References in corpus (6)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Matching Networks for One Shot Learning
• Few-Shot Learning Through an Information Retrieval Lens
• Few-shot Learning with Meta Metric Learners
• Co-Clustering for Multitask Learning

Cited by in corpus (7)

• One-Shot Relational Learning for Knowledge Graphs
• Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
• Bridging the domain gap in cross-lingual document classification
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
• FLEX: Unifying Evaluation for Few-Shot NLP
• Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models
• Learning to Profile: User Meta-Profile Network for Few-Shot Learning