Mining activation force defined dependency patterns for relation extraction

作者：

Highlights：

• A new trigger words identification method is defined based on word activation force.

• A unique representation of activation force defined dependency pattern is proposed.

• Two-level semantic drift suppressing strategy is adopted.

• Experimental result verifies the AFDDP is a good representation of relations.

摘要

•A new trigger words identification method is defined based on word activation force.•A unique representation of activation force defined dependency pattern is proposed.•Two-level semantic drift suppressing strategy is adopted.•Experimental result verifies the AFDDP is a good representation of relations.

论文关键词：Relation extraction,Pattern learning,Trigger word,Activation force

论文评审过程：Received 21 March 2014, Revised 19 June 2015, Accepted 20 June 2015, Available online 24 June 2015, Version of Record 31 July 2015.

论文官网地址：https://doi.org/10.1016/j.knosys.2015.06.012