A deep learning based method benefiting from characteristics of patents for semantic relation classification

作者：

Highlights：

• The unique characteristics of patents are highlighted via comparison.

• A customized deep-learning model is proposed to leverage such characteristics.

• The connection between entity pairs is measured on the basis of associated rules.

• The proposed model outperforms prior models on semantic relation classification.

摘要

•The unique characteristics of patents are highlighted via comparison.•A customized deep-learning model is proposed to leverage such characteristics.•The connection between entity pairs is measured on the basis of associated rules.•The proposed model outperforms prior models on semantic relation classification.

论文关键词：Semantic relation classification,Deep learning,Linguistic characteristics,Similarity measure,Patent analysis

论文评审过程：Received 16 January 2021, Revised 25 June 2022, Accepted 29 June 2022, Available online 13 July 2022, Version of Record 13 July 2022.

论文官网地址：https://doi.org/10.1016/j.joi.2022.101312