Learning how to Active Learn: A Deep Reinforcement Learning Approach

08/08/2017
by   Meng Fang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/08/2020

LTP: A New Active Learning Strategy for Bert-CRF Based Named Entity Recognition

In recent years, deep learning has achieved great success in many natura...
research
11/18/2019

Bias-Aware Heapified Policy for Active Learning

The data efficiency of learning-based algorithms is more and more import...
research
07/09/2020

IALE: Imitating Active Learner Ensembles

Active learning (AL) prioritizes the labeling of the most informative da...
research
06/27/2019

Deep Active Learning with Adaptive Acquisition

Model selection is treated as a standard performance boosting step in ma...
research
07/09/2018

Evaluating Active Learning Heuristics for Sequential Diagnosis

Given a malfunctioning system, sequential diagnosis aims at identifying ...
research
11/12/2020

Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions

We study the problem of medical symptoms recognition from patient text, ...
research
01/11/2022

Active Reinforcement Learning – A Roadmap Towards Curious Classifier Systems for Self-Adaptation

Intelligent systems have the ability to improve their behaviour over tim...

Please sign up or login with your details

Forgot password? Click here to reset