📅  最后修改于: 2022-03-11 14:47:12.231000             🧑  作者: Mango
import spacy
import deplacy
en = spacy.load('en_core_web_sm')
text = "This all encompassing experience wore off for a moment and in that moment, my awareness came gasping to the surface of the hallucination and I was able to consider momentarily that I had killed myself by taking an outrageous dose of an online drug and this was the most pathetic death experience of all time."
doc = en(text)
#deplacy.render(doc)
seen = set() # keep track of covered words
chunks = []
for sent in doc.sents:
heads = [cc for cc in sent.root.children if cc.dep_ == 'conj']
for head in heads:
words = [ww for ww in head.subtree]
for word in words:
seen.add(word)
chunk = (' '.join([ww.text for ww in words]))
chunks.append( (head.i, chunk) )
unseen = [ww for ww in sent if ww not in seen]
chunk = ' '.join([ww.text for ww in unseen])
chunks.append( (sent.root.i, chunk) )
chunks = sorted(chunks, key=lambda x: x[0])
for ii, chunk in chunks:
print(chunk)