Spatial Information Extraction from Short Messages
作者：
Highlights：
• Proposition of original methods for Spatial Entity/Relation extraction.
• Extraction of new variations of spatial entities from SMS and tweets.
• Extraction of new spatial relations, and new variations of spatial relations.
• Our method achieved an F-measure score of 0.84 and 0.86 for SMS and tweets.
• Our method outperforms the state-of-the-art tools (i.e. Polyglot, Stanford NER).
摘要
•Proposition of original methods for Spatial Entity/Relation extraction.•Extraction of new variations of spatial entities from SMS and tweets.•Extraction of new spatial relations, and new variations of spatial relations.•Our method achieved an F-measure score of 0.84 and 0.86 for SMS and tweets.•Our method outperforms the state-of-the-art tools (i.e. Polyglot, Stanford NER).
论文关键词：Spatial entities,Spatial relations,Similarity measures,Short message corpora,Text mining
论文评审过程：Received 18 July 2017, Revised 4 October 2017, Accepted 10 November 2017, Available online 16 November 2017, Version of Record 1 December 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.025
