Last active
June 28, 2020 17:50
-
-
Save aniruddha27/d796631e54d8b49c906aa03bfc5640e5 to your computer and use it in GitHub Desktop.
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
# rule 1 modified function | |
def rule1_mod(text): | |
doc = nlp(text) | |
sent = [] | |
for token in doc: | |
# root word | |
if (token.pos_=='VERB'): | |
phrase ='' | |
# only extract noun or pronoun subjects | |
for sub_tok in token.lefts: | |
if (sub_tok.dep_ in ['nsubj','nsubjpass']) and (sub_tok.pos_ in ['NOUN','PROPN','PRON']): | |
# look for subject modifier | |
adj = rule2_mod(text,sub_tok.i) | |
phrase += adj + ' ' + sub_tok.text | |
# save the root word of the word | |
phrase += ' '+token.lemma_ | |
# check for noun or pronoun direct objects | |
for sub_tok in token.rights: | |
if (sub_tok.dep_ in ['dobj']) and (sub_tok.pos_ in ['NOUN','PROPN']): | |
# look for object modifier | |
adj = rule2_mod(text,sub_tok.i) | |
phrase += adj+' '+sub_tok.text | |
sent.append(phrase) | |
return sent |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment