Collective disambiguation in entity linking based on topic coherence in semantic graphs

作者：

Highlights：

• Collective disambiguation based on semantic graphs from DBpedia.

• An efficient knowledge base exploration algorithm based on bidirectional search.

• Relevance model based on the degree of centrality and semantic similarity.

• A candidate generation algorithm that builds coherence on candidate entities.

• ABACO outperforms other annotators for medium/large documents.

摘要

•Collective disambiguation based on semantic graphs from DBpedia.•An efficient knowledge base exploration algorithm based on bidirectional search.•Relevance model based on the degree of centrality and semantic similarity.•A candidate generation algorithm that builds coherence on candidate entities.•ABACO outperforms other annotators for medium/large documents.

论文关键词：Entity linking,Semantic annotation,Topic coherence,Named entity disambiguation

论文评审过程：Received 17 September 2019, Revised 22 April 2020, Accepted 23 April 2020, Available online 27 April 2020, Version of Record 30 April 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105967