search

TIBHannover / ojsGeo

OJS Geoplugin
https://projects.tib.eu/komet/
GNU General Public License v3.0
3 stars 3 forks source link

Make a suggestion for geospatial extent with a Gazetteer based on title and abstract of a submission #10

Open nuest opened 3 years ago

nuest commented 3 years ago

Antrag: "Die automatische Extraktion unterstützt hochgeladene Geodaten, Links zu ausgewählten Diensten, und die Herleitung von Geodaten über Titel und Abstract des Artikels mit einem Gazetteer."

Feature:

nuest commented 3 years ago

Extracting and modeling geographic information from scientific articles > https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0244918

Just point data, tool: https://github.com/eacheson/pyscine

Papadias, E., Kokla, M., and Tomai, E.: Educing knowledge from text: semantic information extraction of spatial concepts and places, AGILE GIScience Ser., 2, 38, https://doi.org/10.5194/agile-giss-2-38-2021

Xuke Hu, Hussein S. Al-Olimat, Jens Kersten, Matti Wiegmann, Friederike Klan, Yeran Sun & Hongchao Fan (2021) GazPNE: annotation-free deep learning for place name extraction from microblogs leveraging gazetteer and synthetic data by rules, International Journal of Geographical Information Science, https://10.1080/13658816.2021.1947507

image

nuest commented 3 years ago

See what geoextent has to offer by then in terms of extracting from text: https://github.com/o2r-project/geoextent/issues/119

nuest commented 3 years ago

Moved to #2

nuest commented 7 months ago

Mordecai 3: A Neural Geoparser and Event Geocoder

Andrew Halterman

Mordecai3 is a new end-to-end text geoparser and event geolocation system. The system performs toponym resolution using a new neural ranking model to resolve a place name extracted from a document to its entry in the Geonames gazetteer. It also performs event geocoding, the process of linking events reported in text with the place names where they are reported to occur, using an off-the-shelf question-answering model. The toponym resolution model is trained on a diverse set of existing training data, along with several thousand newly annotated examples. The paper describes the model, its training process, and performance comparisons with existing geoparsers. The system is available as an open source Python library, Mordecai 3, and replaces an earlier geoparser, Mordecai v2, one of the most widely used text geoparsers (Halterman 2017).

image

This could also be a good starting point to find other services/tools: https://app.litmaps.com/seed/258008648