def read_corenlp_doc(filename, verbose=True):
if verbose:
log.info('Reading CoreNLP document from {}'.format(filename))
input_xml = smart_file_handler(filename)
xml_parser = etree.XMLParser(target=CoreNLPTarget())
sents, corefs = etree.parse(input_xml, xml_parser)
doc_name = splitext(basename(filename))[0]
doc = Document.construct(doc_name, sents, corefs)
input_xml.close()
return doc
def read_doc_from_ontonotes(coref_doc, name_doc, verbose=True):
doc_id = coref_doc.document_id.split('@')[0]
assert doc_id == name_doc.document_id.split('@')[0], \
'{} and {} do not have the same document_id'.format(coref_doc, name_doc)
if verbose:
log.info('Reading ontonotes document {}'.format(doc_id))
conll_file_path = join(ontonotes_annotations_source, doc_id + '.depparse')
all_sents = read_conll_depparse(conll_file_path)
all_corefs = read_coref_doc(coref_doc)
doc_name = doc_id.split('/')[-1]
doc = Document.construct(doc_name, all_sents, all_corefs)
for name_entity in read_name_doc(name_doc):
add_name_entity_to_doc(doc, name_entity)
return doc
