DEFI-COLaF - Theatre-17e

Thibault Clérice and Simon Gabay

Pipeline

Don't use the latest versions of python. 3.9 is a safe choice:

virtualenv -p python3.9 env

Install packages

pip install -r requirements.txt

Run scripts in the order of the numbering.

To run the NER script, you need to download the final-model.pt here and put it in a directory called models.

Annotation is CC-BY. Images belong to the digital libraries.

Name		Name	Last commit message	Last commit date
Latest commit History 37 Commits
NER		NER
XSLT		XSLT
books		books
origReg		origReg
tei-long-s		tei-long-s
tei		tei
tsv		tsv
txt		txt
.gitattributes		.gitattributes
.gitignore		.gitignore
CITATION.CFF		CITATION.CFF
Graphs.ipynb		Graphs.ipynb
README.md		README.md
Stats.ipynb		Stats.ipynb
Step 00 - TEI Generator.ipynb		Step 00 - TEI Generator.ipynb
Step 01 - Get plain text.ipynb		Step 01 - Get plain text.ipynb
Step 02 - Get Plots.ipynb		Step 02 - Get Plots.ipynb
Step 04 - segment_text.py		Step 04 - segment_text.py
Step 05 - run_ner.py		Step 05 - run_ner.py
TEI Generator.ipynb		TEI Generator.ipynb
TheatreLFSV2.xpr		TheatreLFSV2.xpr
metadata.tsv		metadata.tsv
quality_control.py		quality_control.py
requirements.txt		requirements.txt
rtk-script.py		rtk-script.py
template.jinja		template.jinja