This repository contains Named Entity Recognition (NER) models for location data forked and augmented from the Apache OpenNLP project, trained against the NSF Polar CyberInfrastructure data contributed to the NIST TREC Dynamic Domain Working Group.
In addition, a custom MIME type definition for the Tika GeoTopicParser is provided so that *.geot files can be parsed using the GeoTopicParser. *.geot flies are just text/plain files with text that includes location information.
Finally, a sample set of *.geot files are provided, currently there exists one from the Polar domain.
Send them to Chris A. Mattmann.
- Yun Li, USC
- Chris A. Mattmann, JPL
This project began as the CSCI 572 project of Yun Li on the NSF Polar CyberInfrastructure project at USC under the supervision of Chris Mattmann. You can find Yun's original code base here.
This work was sponsored by the National Science Foundation under funded projects PLR-1348450 and PLR-144562.