Context-sensitive gender inference of named entities in text

作者：

Highlights：

• We create four open-source datasets for identifying the gender of named entities.

• Propose a novel transformer-based architecture for gender tagging of named entities.

• Present multiple supervised and unsupervised learning baselines for gender inference.

• Context-sensitive supervised learning outperforms database-reliant gender tagging.

摘要

•We create four open-source datasets for identifying the gender of named entities.•Propose a novel transformer-based architecture for gender tagging of named entities.•Present multiple supervised and unsupervised learning baselines for gender inference.•Context-sensitive supervised learning outperforms database-reliant gender tagging.

论文关键词：Gender identification,Gender tagging,Gender inference,68T50,68U01

论文评审过程：Received 8 July 2020, Revised 25 September 2020, Accepted 23 October 2020, Available online 11 November 2020, Version of Record 11 November 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102423