BriefGPT.xyz
Jun, 2022
基于深度强化学习的依存句法分析与回溯
Dependency Parsing with Backtracking using Deep Reinforcement Learning
HTML
PDF
Franck Dary, Maxime Petit, Alexis Nasr
TL;DR
该论文研究了如何利用强化学习的方法，通过允许算法回溯并探索替代解决方案来克服自然语言处理中贪婪算法的误差传播问题，并运用于词性标注和依存分析中，表明回溯是防止误差传播的有效手段。
Abstract
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 wher
→