Carlos-Francisco Méndez-Cruz / nlp-preprocessing-pipeline

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
cec413df 1 parent 611eb03b

New terminological tagging for CRFs

Inline Side-by-side
Showing 1 changed file with 4 additions and 4 deletions
......@@ -143,19 +143,19 @@ if __name__ == "__main__":
if word.find('-') > -1:
found = False
repetitions = word.count('-')
#print("repetitions: {}".format(repetitions))
print("repetitions: {}".format(repetitions))
wordOrig = word
for i in range(0, repetitions):
wordOrig = wordOrig.replace('-', ' ', 1)
#print("Word: {}".format(wordOrig))
print("Word: {}".format(wordOrig))
if wordOrig in hashTermsOrig[termTag]:
#print("WordOrig: {}".format(wordOrig))
print("WordOrig: {}".format(wordOrig))
found = True
line = ''
for w, l in zip(word.split('-'), lemma.split('-')):
line += w + '\t' + listLine1[1] + '\t' + l + ' ' + termTag + ' TermTag' + '\n'
line = line.rstrip('\n')
print("Line: {}".format(line))
#print("Line: {}".format(line))
if not found:
line = listLine1[0] + '\t' + listLine1[1] + '\t' + listLine2[0] + ' ' + termTag + ' TermTag'
else:
......