mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
eae35e9b27
- add files to specify rules for German tokenization - change generate_specials.py to generate from an external file (abbrev.de.tab) - copy gazetteer.json from lang_data/en/ - init_model.py - change doc freq threshold to 0 - add train_german_tagger.py - expects conll09-formatted input
74 lines
704 B
Plaintext
74 lines
704 B
Plaintext
,
|
||
\"
|
||
\)
|
||
\]
|
||
\}
|
||
\*
|
||
\!
|
||
\?
|
||
%
|
||
\$
|
||
>
|
||
:
|
||
;
|
||
'
|
||
”
|
||
“
|
||
«
|
||
_
|
||
''
|
||
's
|
||
'S
|
||
’s
|
||
’S
|
||
’
|
||
‘
|
||
°
|
||
€
|
||
\.\.
|
||
\.\.\.
|
||
\.\.\.\.
|
||
(?<=[a-zäöüßÖÄÜ)\]"'´«‘’%\)²“”])\.
|
||
\-\-
|
||
´
|
||
(?<=[0-9])km²
|
||
(?<=[0-9])m²
|
||
(?<=[0-9])cm²
|
||
(?<=[0-9])mm²
|
||
(?<=[0-9])km³
|
||
(?<=[0-9])m³
|
||
(?<=[0-9])cm³
|
||
(?<=[0-9])mm³
|
||
(?<=[0-9])ha
|
||
(?<=[0-9])km
|
||
(?<=[0-9])m
|
||
(?<=[0-9])cm
|
||
(?<=[0-9])mm
|
||
(?<=[0-9])µm
|
||
(?<=[0-9])nm
|
||
(?<=[0-9])yd
|
||
(?<=[0-9])in
|
||
(?<=[0-9])ft
|
||
(?<=[0-9])kg
|
||
(?<=[0-9])g
|
||
(?<=[0-9])mg
|
||
(?<=[0-9])µg
|
||
(?<=[0-9])t
|
||
(?<=[0-9])lb
|
||
(?<=[0-9])oz
|
||
(?<=[0-9])m/s
|
||
(?<=[0-9])km/h
|
||
(?<=[0-9])mph
|
||
(?<=[0-9])°C
|
||
(?<=[0-9])°K
|
||
(?<=[0-9])°F
|
||
(?<=[0-9])hPa
|
||
(?<=[0-9])Pa
|
||
(?<=[0-9])mbar
|
||
(?<=[0-9])mb
|
||
(?<=[0-9])T
|
||
(?<=[0-9])G
|
||
(?<=[0-9])M
|
||
(?<=[0-9])K
|
||
(?<=[0-9])kb
|