Learning how to Active Learn: A Deep Reinforcement Learning Approach

Abstract

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of such methods is limited and moreover, the performance of heuristics varies between datasets. To address these shortcomings, we introduce a novel formulation by reframing the active learning as a reinforcement learning problem and explicitly learning a data selection policy, where the policy takes the role of the active learning heuristic. Importantly, our method allows the selection policy learned using simulation on one language to be transferred to other languages. We demonstrate our method using cross-lingual named entity recognition, observing uniform improvements over traditional active learning.

To appear in EMNLP 2017

References in corpus (2)

• Massively Parallel Methods for Deep Reinforcement Learning
• Move Evaluation in Go Using Deep Convolutional Neural Networks

Cited by in corpus (10)

• Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
• Improving Neural Relation Extraction with Positive and Unlabeled Learning
• Capturing Label Distribution: A Case Study in NLI
• Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
• On the Robustness of Active Learning
• Deep Reinforcement Learning for Fog Computing-based Vehicular System with Multi-operator Support
• Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
• Bias-Aware Heapified Policy for Active Learning
• Deep Reinforcement Learning for Dynamic Spectrum Sensing and Aggregation in Multi-Channel Wireless Networks