Extracting Toponyms from Maps of Jerusalem

From FDHwiki
Jump to navigation Jump to search

Introduction & Motivation

Example of Muqarnas structure

1. Simple Muqarnas: the ceilings have plane surfaces only

Elements defined by Al Kashi
[[]]

Methodology

Create the shapes in 2D

Transform the shapes in 3D

The Arc from the Method of Masons

The 3D Projection

Create the 2D plan and the 3D volume

- Step 1:

- Step 2:

In practice

Project Timeline

Timeframe Task Completion
Week 4
  • Finalize and present project proposals.
    • Toponym extraction project selected.
Week 5
  • Survey SOTA toponym extraction tools.
  • Port MapKurator into Windows-based Python, implement on a sample map.
Week 6
Week 7
  • Create ground truth labels for first map.
Week 8
  • Create ground truth labels for second map.
  • Implement 1:1-matched precision and recall via IoU (geometry) and normalized Levenshtein (text)
Week 9
  • Implement multi-layer pyramid approach to toponym extraction
Week 10
  • Create ground truth labels for third map.
  • Implement toponym rectification and amalgamation algorithms.
Week 11
  • Calculate accuracy statistics for pyramid approach
  • Deliver Midterm presentation.
Week 12
  • Launch Wiki.
  • Group words into toponyms via polygon size and location.
  • Apply NLP tools to correct toponyms.
Week 13
  • Create ground truth labels for fourth map.
  • Calculate final accuracy statistics.
  • Hierarchize final toponyms and develop Voronoi map.
Week 14
  • Prototype toponym-disagreement visualizer.
  • Finalize Wiki and deliver presentation.

Results

Limitations

Future work

Github Repository

Jerusalem Maps EPFL DH405

References

Literature

  • Kim, Jina, et al. "The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps." arXiv preprint arXiv:2306.17059 (2023).
  • Li, Zekun, et al. "An automatic approach for generating rich, linked geo-metadata from historical map images." Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020

Webpages