Path-based reasoning approach for knowledge graph completion using CNN-BiLSTM with attention mechanism

作者：

Highlights：

• Coupled CNN and BiLSTM model accurately encoded paths for knowledge graph completion.

• Combining embeddings of paths between two entities exhibits the semantic relation between the entities.

• Multistep reasoning efficiently predicts the missing links between two entities.

• Attention based CNN-BiLSTM performs better than the recent state-of-the-art path-reasoning methods.

摘要

•Coupled CNN and BiLSTM model accurately encoded paths for knowledge graph completion.•Combining embeddings of paths between two entities exhibits the semantic relation between the entities.•Multistep reasoning efficiently predicts the missing links between two entities.•Attention based CNN-BiLSTM performs better than the recent state-of-the-art path-reasoning methods.

论文关键词：Knowledge graph completion,Link prediction,Path-based reasoning,Low-dimensional embedding

论文评审过程：Received 7 June 2019, Revised 25 August 2019, Accepted 17 September 2019, Available online 26 September 2019, Version of Record 14 October 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112960