def fix_punct(conllu_string): doc = Document() doc.from_conllu_string(conllu_string) fixpunct_block = FixPunct() fixpunct_block.process_document(doc) output_string = doc.to_conllu_string() return output_string
def fix_punct(conllu_string): doc = Document() doc.from_conllu_string(conllu_string) fixpunct_block = FixPunct() fixpunct_block.process_document(doc) output_string = doc.to_conllu_string() output_string = re.sub(r'# sent_id = [0-9]+\n',r'',output_string) # remove udapi sent_id return output_string
def fix_punct(conllu_string):
# Protect possessive apostrophe from being treated as punctuation
conllu_string = re.sub(r"\t'\t([^\t\n]+\tPART\tPOS)", r'\t&udapi_apos;\t\1', conllu_string, flags=re.MULTILINE) # remove udapi sent_id
doc = Document()
doc.from_conllu_string(conllu_string)
fixpunct_block = FixPunct()
fixpunct_block.process_document(doc)
output_string = doc.to_conllu_string()
output_string = output_string.replace('&udapi_apos;',"'")
output_string = re.sub(r'# sent_id = [0-9]+\n',r'',output_string) # remove udapi sent_id
return output_string
def fix_punct(conllu_string):
conllu_string = re.sub(r"\t'\t([^\t\n]+\tPART\tPOS)",
r'\t&udapi_apos;\t\1',
conllu_string,
flags=re.MULTILINE)
conllu_string = re.sub(
r'\t"\t([^\t\n]+\t[^\t\n]+\t[^\t\n]+\t[^\t\n]+\t[^\t\n]+\t[^p])',
r'\t&udapi_quot;\t\1',
conllu_string,
flags=re.MULTILINE)
doc = UdapiDocument()
doc.from_conllu_string(conllu_string)
fixpunct_block = FixPunct()
fixpunct_block.process_document(doc)
output_string = doc.to_conllu_string()
output_string = output_string.replace('&udapi_apos;',
"'").replace('&udapi_quot;', '"')
output_string = re.sub(r'# sent_id = [0-9]+\n', r'',
output_string) # remove udapi sent_id
return output_string
