Created
December 16, 2016 17:15
-
-
Save diyclassics/b24fbd1ad3bbb726387de443fab84956 to your computer and use it in GitHub Desktop.
Backoff lemmatizer edits
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def _define_lemmatizer(self): | |
backoff0 = None | |
backoff1 = IdentityLemmatizer() | |
backoff2 = TrainLemmatizer(model=self.LATIN_OLD_MODEL, backoff=backoff1) | |
backoff3 = PPLemmatizer(regexps=self.latin_verb_patterns, pps=self.latin_pps, backoff=backoff2) | |
backoff4 = UnigramLemmatizer(self.train_sents, backoff=backoff3) | |
backoff5 = RegexpLemmatizer(self.latin_misc_patterns, backoff=backoff4) | |
backoff6 = TrainLemmatizer(model=self.LATIN_MODEL, backoff=backoff5) | |
#backoff7 = BigramPOSLemmatizer(self.pos_train_sents, include=['cum'], backoff=backoff6) | |
lemmatizer = backoff6 | |
return lemmatizer |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment