Using the full-text content of academic articles to identify and evaluate algorithm entities in the domain of natural language processing

作者：

Highlights：

• We extract algorithms from articles and evaluate the impact of algorithms based on the number of papers and mention duration.

• We analyze the algorithms with high impact in different years, and explore the evolution of influence over time.

• Algorithms and sentences we extracted can be used as training data for automatic extraction of algorithms in the future.

摘要

•We extract algorithms from articles and evaluate the impact of algorithms based on the number of papers and mention duration.•We analyze the algorithms with high impact in different years, and explore the evolution of influence over time.•Algorithms and sentences we extracted can be used as training data for automatic extraction of algorithms in the future.

论文关键词：Algorithm entity,Full-text content,Influence of algorithms

论文评审过程：Received 20 February 2020, Revised 25 August 2020, Accepted 27 August 2020, Available online 11 October 2020, Version of Record 11 October 2020.

论文官网地址：https://doi.org/10.1016/j.joi.2020.101091