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
def get_entities(sent): | |
## chunk 1 | |
ent1 = "" | |
ent2 = "" | |
prv_tok_dep = "" # dependency tag of previous token in the sentence | |
prv_tok_text = "" # previous token in the sentence | |
prefix = "" | |
modifier = "" | |
############################################################# | |
for tok in nlp(sent): | |
## chunk 2 | |
# if token is a punctuation mark then move on to the next token | |
if tok.dep_ != "punct": | |
# check: token is a compound word or not | |
if tok.dep_ == "compound": | |
prefix = tok.text | |
# if the previous word was also a 'compound' then add the current word to it | |
if prv_tok_dep == "compound": | |
prefix = prv_tok_text + " "+ tok.text | |
# check: token is a modifier or not | |
if tok.dep_.endswith("mod") == True: | |
modifier = tok.text | |
# if the previous word was also a 'compound' then add the current word to it | |
if prv_tok_dep == "compound": | |
modifier = prv_tok_text + " "+ tok.text | |
## chunk 3 | |
if tok.dep_.find("subj") == True: | |
ent1 = modifier +" "+ prefix + " "+ tok.text | |
prefix = "" | |
modifier = "" | |
prv_tok_dep = "" | |
prv_tok_text = "" | |
## chunk 4 | |
if tok.dep_.find("obj") == True: | |
ent2 = modifier +" "+ prefix +" "+ tok.text | |
## chunk 5 | |
# update variables | |
prv_tok_dep = tok.dep_ | |
prv_tok_text = tok.text | |
############################################################# | |
return [ent1.strip(), ent2.strip()] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment