Learning how to Active Learn: A Deep Reinforcement Learning Approach
Meng Fang,Yuan Li,Trevor Cohn +2 more
- pp 595-605
TLDR
A novel formulation of active learning is introduced 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 activelearning heuristic.Abstract:
© 2017 Association for Computational Linguistics. 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 re-framing 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 more
Citations
More filters
Posted Content
Taking Human out of Learning Applications: A Survey on Automated Machine Learning
Quanming Yao,Mengshuo Wang,Hugo Jair Escalante,Isabelle Guyon,Yi-Qi Hu,Yu-Feng Li,Wei-Wei Tu,Qiang Yang,Yang Yu +8 more
TL;DR: An up to date survey on AutoML and proposes a general AutoML framework that not only covers most existing approaches to date but also can guide the design for new methods.
Journal ArticleDOI
A survey on active learning and human-in-the-loop deep learning for medical image analysis.
TL;DR: The role that humans might play in the development and deployment of deep learning enabled diagnostic applications is investigated and techniques that will retain a significant input from a human end user are focused on.
Proceedings ArticleDOI
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
TL;DR: The authors explored a deep reinforcement learning strategy to generate the false-positive indicator, where they automatically recognize false positives for each relation type without any supervised information and redistribute them into the negative examples.
Posted Content
Massively Multilingual Transfer for NER
TL;DR: This article proposed two techniques for modulating the transfer, suitable for zero-shot or few-shot learning, respectively, for cross-lingual NER using a large number of models over one or more source languages.
Proceedings ArticleDOI
Massively multilingual transfer for NER
TL;DR: This article proposed two techniques for modulating the transfer, suitable for zero-shot or few-shot learning, respectively, for cross-lingual transfer, and evaluated on named entity recognition.
References
More filters
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Journal ArticleDOI
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more
TL;DR: Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Proceedings ArticleDOI
Convolutional Neural Networks for Sentence Classification
TL;DR: The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
Active Learning Literature Survey
TL;DR: This report provides a general introduction to active learning and a survey of the literature, including a discussion of the scenarios in which queries can be formulated, and an overview of the query strategy frameworks proposed in the literature to date.