jordimas's picture
Initial readme
7b8c2a0
|
raw
history blame
876 Bytes
metadata
language:
  - ca
tags:
  - punctuation prediction
  - punctuation
datasets: softcatala/Europarl-catalan
widget:
  - text: >-
      Ara tenim ratolins de quatre mesos que no són diabètics tot i que solien
      ser-ho va afegir.
    example_title: Catalan
metrics:
  - f1

This model predicts the punctuation of Catalan language.

The model restores the following punctuation markers: "." "," "?" "-" ":"

Results

The performance differs for the single punctuation markers as hyphens and colons, in many cases, are optional and can be substituted by either a comma or a full stop. The model achieves the following F1 scores for the different languages:

Label CA
0 0.99
. 0.93
? 0.76
, 0.82
: 0.64
- 0.89
macro average 0.84