from stanza.server import CoreNLPClient# get noun phrases with tregexdef noun_phrases(_client, _text, _annotators=None): pattern = 'NP' matches = _client.tregex(_text,pattern,annotators=_annotators) print("n".join(["t"+sentence[match_id]['spanString'] for sentence in matches['sentences'] for match_id in sentence]))# English examplewith CoreNLPClient(timeout=30000, memory='16G') as client: englishText = "Albert Einstein was a German-born theoretical physicist. He developed the theory of relativity." print('---') print(englishText) noun_phrases(client,englishText,_annotators="tokenize,ssplit,pos,lemma,parse")# French examplewith CoreNLPClient(properties='french', timeout=30000, memory='16G') as client: frenchText = "Je suis John." print('---') print(frenchText) noun_phrases(client,frenchText,_annotators="tokenize,ssplit,mwt,pos,lemma,parse")
