Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
2021-01-01
SCID: 54.1/zc962kc8
Abstract (AI)
When learned without exploration, local models for structured prediction tasks are subject to exposure bias and cannot be trained without detailed guidance. Active Imitation Learning (AIL), also known in NLP as Dynamic Oracle Learning, is a general technique for working around these issues by allowing the exploration of different outputs at training time.
Key Findings
Research Object
Research Subject
Publication Details
Publication Date
2021-01-01
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF