A hybrid Transformer approach for Chinese NER with features augmentation

作者：

Highlights：

• Propose a hybrid Transformer approach for Chinese NER.

• Take the latent words as the additional features to improve NER task.

• Find an efficient strategy to fine-tune BERT with other modules.

• Apply relative position encodings to improve Transformer.

摘要

•Propose a hybrid Transformer approach for Chinese NER.•Take the latent words as the additional features to improve NER task.•Find an efficient strategy to fine-tune BERT with other modules.•Apply relative position encodings to improve Transformer.

论文关键词：Named entity recognition,Transformer,Bidirectional Encoder Representations from Transformers,Conditional Random Field

论文评审过程：Received 31 March 2022, Revised 19 June 2022, Accepted 1 August 2022, Available online 6 August 2022, Version of Record 9 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118385