Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Learning how to Active Learn: A Deep Reinforcement Learning Approach

Domain:

natural language processing

Record type:

paper
Creator:
FanLi, YuanCoh
Host:avatar
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

Visit

arxiv.org

Tags

Computation and LanguageArtificial IntelligenceMachine Learning

Similar

Learning How to Learn Languages: The Teaching & Learning of African LanguagesDeep Reinforcement Learning Approach for Autonomous Crop Yield Optimization in Precision FarmingEfficient Poverty Mapping using Deep Reinforcement LearningEffectiveness of GeoGebra towards Students’ Active Learning, Performance and Interest to Learn MathematicsApplications of Deep Reinforcement Learning in Communications and Networking: A SurveyThe Implementation of Deep Reinforcement Learning in E-Learning and Distance Learning: Remote Practical Work

Learning How to Learn Languages: The Teaching & Learning of African Languages

Abstract The African continent is home to over a thousand languages, many of whi

Deep Reinforcement Learning Approach for Autonomous Crop Yield Optimization in Precision Farming

Efficient Poverty Mapping using Deep Reinforcement Learning

The combination of high-resolution satellite imagery and machine learning have proven useful in many

Effectiveness of GeoGebra towards Students’ Active Learning, Performance and Interest to Learn Mathematics

The present study explored the effectiveness of GeoGebra in enhancing students’ active learning, per

Applications of Deep Reinforcement Learning in Communications and Networking: A Survey

This paper presents a comprehensive literature review on applications of deep reinforcement learning

The Implementation of Deep Reinforcement Learning in E-Learning and Distance Learning: Remote Practical Work

The world has seen major developments in the field of e-learning and distance learning, especially d