Virtual prompt pre-training for prototype-based few-shot relation extraction

作者：

Highlights：

• Jointly pre-training an entity-relation-aware Language Model and a prompt encoder.

• A novel prompt-based prototype network, using pre-trained virtual prompts.

• Freely employ features with vocabulary-sized dimensions for classification.

摘要

•Jointly pre-training an entity-relation-aware Language Model and a prompt encoder.•A novel prompt-based prototype network, using pre-trained virtual prompts.•Freely employ features with vocabulary-sized dimensions for classification.

论文关键词：Few-shot learning,Information extraction,Prompt tuning,Pre-trained Language Model

论文评审过程：Received 18 July 2022, Revised 20 September 2022, Accepted 25 September 2022, Available online 30 September 2022, Version of Record 11 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118927