Center-shared sliding ensemble of neural networks for syntax analysis of natural language
作者：
Highlights：
• Fixing input sites in ensembles restrict learning movable and distant patterns.
• The new ensemble changes the sites across component classifiers sharing one position.
• The ensemble improves accuracy in learning movable patterns and its lower bound.
• The neural network framework with the ensemble improves accuracy in syntax analysis.
• The framework is accurate as state-of-the-art methods in Spanish dependency parsing.
摘要
•Fixing input sites in ensembles restrict learning movable and distant patterns.•The new ensemble changes the sites across component classifiers sharing one position.•The ensemble improves accuracy in learning movable patterns and its lower bound.•The neural network framework with the ensemble improves accuracy in syntax analysis.•The framework is accurate as state-of-the-art methods in Spanish dependency parsing.
论文关键词：Ensemble,Center-shared sliding,Neural network,Dependency parsing,Grammatical relation
论文评审过程：Received 7 July 2016, Revised 3 April 2017, Accepted 24 April 2017, Available online 25 April 2017, Version of Record 29 April 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.04.048
