The (German) spacy tokenizer does not split on slashes, underscores, or asterisks by default, which is just what I need (so "der/die" results in a single token).
However it does split on parentheses so "dies(und)das" gets split into 5 tokens. Is there a (simple) way to tell the default tokeniser to also not split on parentheses which are enclosed by letters on both sides without a space?
How exactly are those splits on parentheses defined for a tokenizer?
The split on parentheses is defined in this line, where it splits on a parenthesis between two letters:
There's no simple way to remove infix patterns, but you can define a custom tokenizer that does what you want. One way is to copy the infix definition from spacy/lang/de/punctuation.py and modify it:
import re
import spacy
from spacy.tokenizer import Tokenizer
from spacy.lang.char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER, CONCAT_QUOTES, LIST_ELLIPSES, LIST_ICONS
from spacy.lang.de.punctuation import _quotes
from spacy.util import compile_prefix_regex, compile_infix_regex, compile_suffix_regex
def custom_tokenizer(nlp):
infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r'(?<=[{a}])[:<>=](?=[{a}])'.format(a=ALPHA),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\]\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
r"(?<=[0-9])-(?=[0-9])",
]
)
infix_re = compile_infix_regex(infixes)
return Tokenizer(nlp.vocab, prefix_search=nlp.tokenizer.prefix_search,
suffix_search=nlp.tokenizer.suffix_search,
infix_finditer=infix_re.finditer,
token_match=nlp.tokenizer.token_match,
rules=nlp.Defaults.tokenizer_exceptions)
nlp = spacy.load('de')
nlp.tokenizer = custom_tokenizer(nlp)