예제 #1
0
# It is a good idea to study the tagset and its abbreviations for a few minutes.

from pattern.en import parse as parse_en
print(parse_en("the black cats", chunks=False))  # the/DT black/JJ cat/NNS
print("")

# ... where DT = determiner, JJ = adjective, NN = noun.
# This is true for all languages that Pattern supports:

from pattern.de import parse as parse_de
from pattern.es import parse as parse_es
from pattern.fr import parse as parse_fr
from pattern.it import parse as parse_it
from pattern.nl import parse as parse_nl

print(parse_de("die schwarzen Katzen",
               chunks=False))  # die/DT schwarze/JJ Katzen/NNS
print(parse_es("los gatos negros", chunks=False))  # los/DT gatos/NNS negros/JJ
print(parse_fr("les chats noirs", chunks=False))  # les/DT chats/NNS noirs/JJ
print(parse_it("i gatti neri", chunks=False))  # i/DT gatti/NNS neri/JJ
print(parse_nl("de zwarte katten", chunks=False))  # de/DT zwarte/JJ katten/NNS
print("")

# In some cases, this means the original tagset is mapped to Penn Treebank:
# e.g., for German (STTS), Spanish (PAROLE), Dutch (WOTAN).

from pattern.de import STTS
from pattern.es import PAROLE
from pattern.nl import WOTAN

print(parse_de("die schwarzen Katzen", chunks=False, tagset=STTS))
print(parse_es("los gatos negros", chunks=False, tagset=PAROLE))
예제 #2
0
from pattern.en import parse as parse_en
print(parse_en("the black cats", chunks=False))      # the/DT black/JJ cat/NNS
print()


# ... where DT = determiner, JJ = adjective, NN = noun.
# This is true for all languages that Pattern supports:

from pattern.de import parse as parse_de
from pattern.es import parse as parse_es
from pattern.fr import parse as parse_fr
from pattern.it import parse as parse_it
from pattern.nl import parse as parse_nl

# die/DT schwarze/JJ Katzen/NNS
print(parse_de("die schwarzen Katzen", chunks=False))
print(parse_es("los gatos negros", chunks=False))  # los/DT gatos/NNS negros/JJ
print(parse_fr("les chats noirs", chunks=False))  # les/DT chats/NNS noirs/JJ
print(parse_it("i gatti neri", chunks=False))  # i/DT gatti/NNS neri/JJ
print(parse_nl("de zwarte katten", chunks=False))  # de/DT zwarte/JJ katten/NNS
print()

# In some cases, this means the original tagset is mapped to Penn Treebank:
# e.g., for German (STTS), Spanish (PAROLE), Dutch (WOTAN).

from pattern.de import STTS
from pattern.es import PAROLE
from pattern.nl import WOTAN

print(parse_de("die schwarzen Katzen", chunks=False, tagset=STTS))
print(parse_es("los gatos negros", chunks=False, tagset=PAROLE))
예제 #3
0
from pattern.en import parse as parse_en
print(parse_en("the black cats", chunks=False))      # the/DT black/JJ cat/NNS
print()


# ... where DT = determiner, JJ = adjective, NN = noun.
# This is true for all languages that Pattern supports:

from pattern.de import parse as parse_de
from pattern.es import parse as parse_es
from pattern.fr import parse as parse_fr
from pattern.it import parse as parse_it
from pattern.nl import parse as parse_nl

print(parse_de("die schwarzen Katzen", chunks=False)) # die/DT schwarze/JJ Katzen/NNS
print(parse_es("los gatos negros"    , chunks=False)) # los/DT gatos/NNS negros/JJ
print(parse_fr("les chats noirs"     , chunks=False)) # les/DT chats/NNS noirs/JJ
print(parse_it("i gatti neri"        , chunks=False)) # i/DT gatti/NNS neri/JJ
print(parse_nl("de zwarte katten"    , chunks=False)) # de/DT zwarte/JJ katten/NNS
print()

# In some cases, this means the original tagset is mapped to Penn Treebank:
# e.g., for German (STTS), Spanish (PAROLE), Dutch (WOTAN).

from pattern.de import STTS
from pattern.es import PAROLE
from pattern.nl import WOTAN

print(parse_de("die schwarzen Katzen", chunks=False, tagset=STTS))
print(parse_es("los gatos negros"    , chunks=False, tagset=PAROLE))
예제 #4
0
from pattern.en import parse as parse_en
print(parse_en("the black cats", chunks=False))  # the/DT black/JJ cat/NNS
print()

# ... where DT = determiner, JJ = adjective, NN = noun.
# This is true for all languages that Pattern supports:

from pattern.de import parse as parse_de
from pattern.es import parse as parse_es
from pattern.fr import parse as parse_fr
from pattern.it import parse as parse_it
from pattern.nl import parse as parse_nl

# die/DT schwarze/JJ Katzen/NNS
print(parse_de("die schwarzen Katzen", chunks=False))
print(parse_es("los gatos negros", chunks=False))  # los/DT gatos/NNS negros/JJ
print(parse_fr("les chats noirs", chunks=False))  # les/DT chats/NNS noirs/JJ
print(parse_it("i gatti neri", chunks=False))  # i/DT gatti/NNS neri/JJ
print(parse_nl("de zwarte katten", chunks=False))  # de/DT zwarte/JJ katten/NNS
print()

# In some cases, this means the original tagset is mapped to Penn Treebank:
# e.g., for German (STTS), Spanish (PAROLE), Dutch (WOTAN).

from pattern.de import STTS
from pattern.es import PAROLE
from pattern.nl import WOTAN

print(parse_de("die schwarzen Katzen", chunks=False, tagset=STTS))
print(parse_es("los gatos negros", chunks=False, tagset=PAROLE))