Normalisation models

Use the models

Machine Translation Models

Coming soon...

ABA

This alignment-based approach for 17^th-century text normalisation is available on GitHub and a demo (whose word transformation list was obtained on the train subcorpus of FreEM_norm) is provided here.

Publication

Rachel Bawden, Jonathan Poinhos, Eleni Kogkitsidou, Philippe Gambette, Benoît Sagot, Simon Gabay. Automatic Normalisation of Early Modern French. LREC 2022.

Results

Model	Precision %	Precision OOV %
Identity function	72,73	43,00
ABA	95,14	69,50
SMT	97,10±0,02	75,64±0,18
LSTM	96,14±0,08	76,69±0,70
Transformer	95,89±0,07	75,73±0,38
Fonction d’identité + Lefff	86,12	64,84
ABA + Lefff	95,44	73,54
SMT + Lefff	97,24±0,02	78,37±0,20
LSTM + Lefff	96,25±0,10	78,35±0,79
Transformer + Lefff	96,01±0,09	77,51±1,00

Qualitative comparison of results

Using MEDITE, we aligned two automatically normalised versions of the dev subcorpus of FreEM_norm, the first one with the best statistical model, SMT + Lefff and the second one with the best non-statistical approach, ABA + Lefff: result of the comparison.