Dependency Parsing with Backtracking using Deep Reinforcement Learning

Franck Dary, Maxime Petit, Alexis Nasr


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 where new evidence contradicts the solution explored so far. In order to implement such a behavior, we use reinforcement learning and let the algorithm backtrack in cases where such an action gets a better reward than continuing to explore the current solution. We test this idea on both POS tagging and dependency parsing and show that backtracking is an effective means to fight against error propagation.
Anthology ID:
2022.tacl-1.52
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
888–903
Language:
URL:
https://aclanthology.org/2022.tacl-1.52
DOI:
10.1162/tacl_a_00496
Bibkey:
Cite (ACL):
Franck Dary, Maxime Petit, and Alexis Nasr. 2022. Dependency Parsing with Backtracking using Deep Reinforcement Learning. Transactions of the Association for Computational Linguistics, 10:888–903.
Cite (Informal):
Dependency Parsing with Backtracking using Deep Reinforcement Learning (Dary et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.52.pdf