Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
This addresses error propagation in NLP for dependency parsing, but it is incremental as it builds on an existing high-performance parser.
The paper tackled error propagation in greedy dependency parsing by applying reinforcement learning, which improved the labeled and unlabeled dependency accuracy of the Stanford Neural Dependency Parser while maintaining efficiency.
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.