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

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
f1f59f7a 1 parent f612c3cc

New terminological tagging for CRFs

Inline Side-by-side
Showing 1 changed file with 0 additions and 27 deletions
...@@ -158,33 +158,6 @@ if __name__ == "__main__": ...@@ -158,33 +158,6 @@ if __name__ == "__main__":
158 break 158 break
159 #print("Line: {}".format(line)) 159 #print("Line: {}".format(line))
160 if not found: 160 if not found:
161 - wordOrig = word
162 - for i in range(repetitions, 0, -1):
163 - wordOrig = wordOrig.replace('-', ' ', i)
164 - print("Word: {}".format(wordOrig))
165 - if wordOrig in hashTermsOrig[termTag]:
166 - print("WordOrig: {}".format(wordOrig))
167 - found = True
168 - line = ''
169 - for w, l in zip(word.split('-'), lemma.split('-')):
170 - line += w + '\t' + listLine1[
171 - 1] + '\t' + l + ' ' + termTag + ' TermTag' + '\n'
172 - line = line.rstrip('\n')
173 - break
174 - if not found:
175 - for i in range(1, repetitions + 1):
176 - wordOrig = word.replace('-', ' ', i)
177 - print("Word: {}".format(wordOrig))
178 - if wordOrig in hashTermsOrig[termTag]:
179 - print("WordOrig: {}".format(wordOrig))
180 - found = True
181 - line = ''
182 - for w, l in zip(word.split('-'), lemma.split('-')):
183 - line += w + '\t' + listLine1[
184 - 1] + '\t' + l + ' ' + termTag + ' TermTag' + '\n'
185 - line = line.rstrip('\n')
186 - break
187 - if not found:
188 line = listLine1[0] + '\t' + listLine1[1] + '\t' + listLine2[0] + ' ' + termTag + ' TermTag' 161 line = listLine1[0] + '\t' + listLine1[1] + '\t' + listLine2[0] + ' ' + termTag + ' TermTag'
189 else: 162 else:
190 line = listLine1[0] + '\t' + listLine1[1] + '\t' + listLine2[0] + ' ' + termTag + ' TermTag' 163 line = listLine1[0] + '\t' + listLine1[1] + '\t' + listLine2[0] + ' ' + termTag + ' TermTag'
......