def tag(self, sent, tagregex=True, deftag='XX', verbose=False):
kalimat = sent.encode('utf-8')
text = self.regexTokenizer(kalimat.lower().strip())
## :> --___<<IMPORTANT>>___--
## Untuk beberapa hal default tagger harus dibiarkan 'XX'
## dengan tujuan identifikasi Entitas
backoff_tagger = DefaultTagger(deftag)
if tagregex:
regexp_tagger = RegexpTagger(patterns.regex_patterns,backoff=backoff_tagger)
unigram_tagger = UnigramTagger(self.reader_train, backoff=regexp_tagger)
else:
unigram_tagger = UnigramTagger(self.reader_train, backoff=backoff_tagger)
bigram_tagger = BigramTagger(self.reader_train, backoff=unigram_tagger)
trigram_tagger = TrigramTagger(self.reader_train, backoff=bigram_tagger)
"""
# Menggunakan dataset pan localization bahasa indonesia "UI-1M-tagged.txt"
# kombinasi proses tagging diatas menghasilkan tingkat akurasi:
# dengan regextagger: 77%
# tanpa regextagger : > 90%
"""
if verbose:
# Semakin besar dokumen, semakin lama proses perhitungan akurasi
# disarankan hanya untuk testing
print ("Calculating Tagger Accuracy...")
self.tagAccuracy = trigram_tagger.evaluate(self.test_sent)
print ("Accuracy is: %s" % (self.tagAccuracy))
return trigram_tagger.tag(text)
def tag(self, sent, tagregex=True, deftag='XX', verbose=False):
kalimat = sent.encode('utf-8')
## :> --___<<IMPORTANT>>___--
## Untuk beberapa hal default tagger harus dibiarkan 'XX'
## dengan tujuan identifikasi Entitas
backoff_tagger = DefaultTagger(deftag)
if tagregex:
text = self.regexTokenizer(kalimat.lower().strip())
regexp_tagger = RegexpTagger(patterns.regex_patterns,backoff=backoff_tagger)
unigram_tagger = UnigramTagger(self.reader_train, backoff=regexp_tagger)
else:
text = self.wordTokenizer(kalimat.lower().strip())
unigram_tagger = UnigramTagger(self.reader_train, backoff=backoff_tagger)
bigram_tagger = BigramTagger(self.reader_train, backoff=unigram_tagger)
trigram_tagger = TrigramTagger(self.reader_train, backoff=bigram_tagger)
"""
# Menggunakan dataset pan localization bahasa indonesia "UI-1M-tagged.txt"
# kombinasi proses tagging diatas menghasilkan tingkat akurasi:
# dengan regextagger: < 77%
# tanpa regextagger : > 83%
"""
if verbose:
# Semakin besar dokumen, semakin lama proses perhitungan akurasi
# disarankan hanya untuk testing
print "Calculating Tagger Accuracy..."
self.tagAccuracy = trigram_tagger.evaluate(self.test_sent)
print "Accuracy is: %4.2f %%" % (100.0 * self.tagAccuracy)
return trigram_tagger.tag(text)
def train_trigram(data):
trigram_tagger = TrigramTagger(data)
with open(os.path.join(PACKDIR, "nib_marburg", "trigram.pickle"),
"wb") as f:
pickle.dump(trigram_tagger, f)
res = trigram_tagger.tag(
"uns ist in alten mæren wunders vil geseit".split(" "))
print(res)
