NER and Linking of Ancient and Historic Places
An Named-entity Recognition tool that can recognize historical places names in a text.
Table of Contents
- About the Project
- Project Status
- Getting Started
- Release Process
- How to Get Help
- Further Reading
- Contributing
- License
- Authors
About the Project
This project is a web application that can recognize historical places names in a text. User can click on the recognized results and find out completed details of each historical place recognized.
All dataset are from Pleiades, At present, it has extensive coverage for the Greek and Roman world, and is expanding into Ancient Near Eastern, Byzantine, Celtic, Early Islamic, and Early Medieval geography.
This project includes:
- A completed model built by using Spacy
- A web application
Project Status
The specific domain model of historical places names is completed.
Web pages mostly done, need to add more details.
Evaluations not completed yet, need more tests.
Getting Started
Environment:
python 3.7Dependencies
This project mainly used Spacy and Flask for external libraries.
More others details see requirements.txt.
Getting the Source
This project is hosted on GitHub. You can clone this project directly using this command:
git clone https://github.com/lamharrison/NER-and-Linking-of-Ancient-and-Historic-Places.git
Installation
Instructions for how to install the project.
# load the web directory.
cd web/
# run app.py
python app.py
# The web application should be deploy on localhost now.
# Click on the localhost address to use the web application.
Usage
When enter the localhost web application, it should be looked like this.
After entering your historical text, click on submit button, results come out.
Click on place names recognized, it would jump to place information details page.
Release Process
Version 1.0.0.
How to Get Help
Please post on issues section if you need any helps.
Contributing
We encourage public contributions! Please review CODE_OF_CONDUCT.md for details on our code of conduct and development process.
Further Reading and References
License
Copyright (c) 2020 Dr. Andreas Vlachidis, Zhishu Lin.
This project is licensed under the MIT license - see LICENSE.md file for details.