Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

2017-02-22 · EACL 2017 4 · Minh Le, Antske Fokkens

Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies of the Stanford Neural Dependency Parser, a high performance greedy parser, while maintaining its efficiency. We investigate the portion of errors which are the result of error propagation and confirm that reinforcement learning reduces the occurrence of error propagation.

📄 PDF Abstract BibTeX arXiv:1702.06794

Code (1)

https://bitbucket.org/cltl/redep-java 공식 구현

Tasks

Dependency Parsing reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Dependency Parsing with Backtracking using Deep Reinforcement Learning

2022-06-28 · Franck Dary, Maxime Petit, Alexis Nasr

Greedy algorithms for NLP such as transition based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new ev…

Deep Reinforcement Learning Dependency Parsing POS POS Tagging+3

Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via Rollout

2019-11-04 · Xubo Yue, Raed Al Kontar

Lookahead, also known as non-myopic, Bayesian optimization (BO) aims to find optimal sampling policies through solving a dynamic program (DP) that maximizes a long-term reward over a rolling horizon. Though promising, lo…

Bayesian Optimization

MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents

2020-10-15 · NeurIPS 2021 12 · Stephen Chung

Nearly all state-of-the-art deep learning algorithms rely on error backpropagation, which is generally regarded as biologically implausible. An alternative way of training an artificial neural network is through treating…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Reinforcement Learning-based Radio Resource Allocation and Beam Management under Location Uncertainty in 5G mmWave Networks

2022-04-23 · Yujie Yao, Hao Zhou, Melike Erol-Kantarci

Millimeter Wave (mmWave) is an important part of 5G new radio (NR), in which highly directional beams are adapted to compensate for the substantial propagation loss based on UE locations. However, the location informatio…

Clustering Deep Reinforcement Learning Management reinforcement-learning+2

Sign and Relevance Learning

2021-10-14 · Sama Daryanavard, Bernd Porr

Standard models of biologically realistic or biologically inspired reinforcement learning employ a global error signal, which implies the use of shallow networks. On the other hand, error backpropagation allows the use o…

reinforcement-learning Reinforcement Learning (RL)