Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods

Aditya Sharma, Zarana Parekh, Partha Talukdar


Abstract
RLIE-DQN is a recently proposed Reinforcement Learning-based Information Extraction (IE) technique which is able to incorporate external evidence during the extraction process. RLIE-DQN trains a single agent sequentially, training on one instance at a time. This results in significant training slowdown which is undesirable. We leverage recent advances in parallel RL training using asynchronous methods and propose RLIE-A3C. RLIE-A3C trains multiple agents in parallel and is able to achieve upto 6x training speedup over RLIE-DQN, while suffering no loss in average accuracy.
Anthology ID:
D17-1281
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2658–2663
Language:
URL:
https://www.aclweb.org/anthology/D17-1281
DOI:
10.18653/v1/D17-1281
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1281.pdf
Attachment:
 D17-1281.Attachment.zip