A Natural Language Processing Approach to Understanding Context in the Extraction and GeoCoding of Historical Floods, Storms, and Adaptation Measures

作者：

Highlights：

• ●Leverage NLP to create a domain specific NER model from a diverse set of online media●Rely on domain-specific statistical models, linguistics, and rule-based matching●Bolsters the acceptable corpus formats and maintains similar accuracy and reliability●Result is a highly reliable and geographically relevant dataset●Find precise locations of nearly 650k flood events in the US in the past two decades

摘要

●Leverage NLP to create a domain specific NER model from a diverse set of online media●Rely on domain-specific statistical models, linguistics, and rule-based matching●Bolsters the acceptable corpus formats and maintains similar accuracy and reliability●Result is a highly reliable and geographically relevant dataset●Find precise locations of nearly 650k flood events in the US in the past two decades

论文关键词：Information Extraction,Natural language processing,Floods,Machine Learning,Newspapers

论文评审过程：Received 28 June 2021, Accepted 29 August 2021, Available online 9 October 2021, Version of Record 9 October 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102735