49 lines
1.0 KiB
Plaintext
49 lines
1.0 KiB
Plaintext
|
.. Copyright (C) 2001-2023 NLTK Project
|
||
|
|
.. For license information, see LICENSE.TXT
|
||
|
|
|
||
|
|
============================
|
||
|
|
Japanese Language Processing
|
||
|
|
============================
|
||
|
|
|
||
|
|
>>> from nltk import *
|
||
|
|
|
||
|
|
-------------
|
||
|
|
Corpus Access
|
||
|
|
-------------
|
||
|
|
|
||
|
|
KNB Corpus
|
||
|
|
----------
|
||
|
|
|
||
|
|
>>> from nltk.corpus import knbc
|
||
|
|
|
||
|
|
Access the words: this should produce a list of strings:
|
||
|
|
|
||
|
|
>>> type(knbc.words()[0]) is not bytes
|
||
|
|
True
|
||
|
|
|
||
|
|
Access the sentences: this should produce a list of lists of strings:
|
||
|
|
|
||
|
|
>>> type(knbc.sents()[0][0]) is not bytes
|
||
|
|
True
|
||
|
|
|
||
|
|
Access the tagged words: this should produce a list of word, tag pairs:
|
||
|
|
|
||
|
|
>>> type(knbc.tagged_words()[0])
|
||
|
|
<... 'tuple'>
|
||
|
|
|
||
|
|
Access the tagged sentences: this should produce a list of lists of word, tag pairs:
|
||
|
|
|
||
|
|
>>> type(knbc.tagged_sents()[0][0])
|
||
|
|
<... 'tuple'>
|
||
|
|
|
||
|
|
|
||
|
|
JEITA Corpus
|
||
|
|
------------
|
||
|
|
|
||
|
|
>>> from nltk.corpus import jeita
|
||
|
|
|
||
|
|
Access the tagged words: this should produce a list of word, tag pairs, where a tag is a string:
|
||
|
|
|
||
|
|
>>> type(jeita.tagged_words()[0][1]) is not bytes
|
||
|
|
True
|