- Notifications
You must be signed in to change notification settings - Fork1.1k
Open
Description
Hi, in cases like "3. Minute" the sentence wrongly ends at "3." according to Punkt.
I see you have an effective list of words (notably months) inpackages/tokenizers/punkt_tab/german/collocations.tab but it is incomplete. It would be useful to add the following time expressions:
##number## sekunde##number## minute##number## stunde##number## tag##number## woche##number## monat##number## jahrI'm not sure how to proceed, can I open a PR to change the file directly or are other steps involved?
Metadata
Metadata
Assignees
Labels
No labels