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

M.N. Le, A.S. Fokkens

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

108 Downloads (Pure)

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Place of PublicationValencia, Spain
Pages677-687
Number of pages10
Volume1
Publication statusPublished - Apr 2017

Fingerprint

Dive into the research topics of 'Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing'. Together they form a unique fingerprint.

Cite this