Network measures: A new paradigm towards reliable novel word sense detection

作者：

Highlights：

• First ever attempt to apply complex network theory for precise novel sense detection.

• Complex network measures boosts the precision values from 0.23-0.32 to 0.74-0.86.

• Network measures are more useful than network embedding measures for this task.

• Gold standard dataset prepared by us for this task are made publicly available.

摘要

•First ever attempt to apply complex network theory for precise novel sense detection.•Complex network measures boosts the precision values from 0.23-0.32 to 0.74-0.86.•Network measures are more useful than network embedding measures for this task.•Gold standard dataset prepared by us for this task are made publicly available.

论文关键词：Novel sense detection,Distributional thesaurus network,Complex network measures

论文评审过程：Received 5 April 2019, Revised 17 November 2019, Accepted 18 November 2019, Available online 28 November 2019, Version of Record 20 October 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2019.102173