Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification

Abstract

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.

arXiv comment11pages, 5 figures, accepted to EMNLP 2019

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Theoretical Models of Learning to Learn
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Multi-Instance Multi-Label Learning
• Deep Reinforcement Learning that Matters
• Context-Dependent Fine-Grained Entity Type Tagging

Cited by in corpus (2)

• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• $k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection