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

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
ef323801 1 parent 90d0b668

New terminological tagging for CRFs

Inline Side-by-side
Showing 1 changed file with 2 additions and 0 deletions
...@@ -135,6 +135,8 @@ if __name__ == "__main__": ...@@ -135,6 +135,8 @@ if __name__ == "__main__":
135 for termTag in hashTerms: 135 for termTag in hashTerms:
136 if word in hashTerms[termTag]: 136 if word in hashTerms[termTag]:
137 wordOrig = word.replace('-', ' ') 137 wordOrig = word.replace('-', ' ')
138 + print("Word: {}".format(word))
139 + print("WordOrig: {}".format(wordOrig))
138 if wordOrig in hashTermsOrig[termTag]: 140 if wordOrig in hashTermsOrig[termTag]:
139 line = '' 141 line = ''
140 for w, l in zip(word.split('-'), lemma.split('-')): 142 for w, l in zip(word.split('-'), lemma.split('-')):
......