mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
6c498f9ff4
* Add words to portuguese language _num_words * Add words to portuguese language _num_words * Portuguese - Add/remove stopwords, fix tokenizer, add currency symbols * Extended punctuation and norm_exceptions in the Portuguese language
24 lines
933 B
Python
24 lines
933 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
# These exceptions are used to add NORM values based on a token's ORTH value.
|
|
# Individual languages can also add their own exceptions and overwrite them -
|
|
# for example, British vs. American spelling in English.
|
|
|
|
# Norms are only set if no alternative is provided in the tokenizer exceptions.
|
|
# Note that this does not change any other token attributes. Its main purpose
|
|
# is to normalise the word representations so that equivalent tokens receive
|
|
# similar representations. For example: $ and € are very different, but they're
|
|
# both currency symbols. By normalising currency symbols to $, all symbols are
|
|
# seen as similar, no matter how common they are in the training data.
|
|
|
|
|
|
NORM_EXCEPTIONS = {
|
|
"R$": "$", # Real
|
|
"r$": "$", # Real
|
|
"Cz$": "$", # Cruzado
|
|
"cz$": "$", # Cruzado
|
|
"NCz$": "$", # Cruzado Novo
|
|
"ncz$": "$" # Cruzado Novo
|
|
}
|