代码之家 › 专栏 › 技术社区 › HJA24

空间否定与依赖分析

spacy python

HJA24 · 技术社区 · 7 年前

情感词在否定的语义范围内表现出很大的不同。我想用一个稍微修改过的版本 Das and Chen (2001) 它们能检测出诸如 , 不 ,和然后在否定和从句级标点符号之间出现的每个单词后面加一个“neg”后缀。我想从spaCy创建类似的依赖解析。

import spacy
from spacy import displacy

nlp = spacy.load('en')
doc = nlp(u'$AAPL is Ã³Ã³Ã³Ã³Ã³pen to âTalkâ about patents with GOOG definitely not the treatment #samsung got:-) heh')

options = {'compact': True, 'color': 'black', 'font': 'Arial'}
displacy.serve(doc, style='dep', options=options)

可视化的依赖关系路径:

很好,在依赖标记方案中存在一个否定修饰符; NEG

为了识别否定,我使用以下方法:

 negation = [tok for tok in doc if tok.dep_ == 'neg']

现在我要检索否定的范围。

import spacy
from spacy import displacy
import pandas as pd

nlp = spacy.load("en_core_web_sm")
doc = nlp(u'AAPL is Ã³Ã³Ã³Ã³Ã³pen to Talk about patents with GOOG definitely not the treatment got')

print('DEPENDENCY RELATIONS')
print('Key: ')
print('TEXT, DEP, HEAD_TEXT, HEAD_POS, CHILDREN')

for token in doc:
    print(token.text, token.dep_, token.head.text, token.head.pos_,
      [child for child in token.children])

这将产生以下输出:

DEPENDENCY RELATIONS
Key: 
TEXT, DEP, HEAD_TEXT, HEAD_POS, CHILDREN
AAPL nsubj is VERB []
is ROOT is VERB [AAPL, Ã³Ã³Ã³Ã³Ã³pen, got]
Ã³Ã³Ã³Ã³Ã³pen acomp is VERB [to]
to prep Ã³Ã³Ã³Ã³Ã³pen ADJ [Talk]
Talk pobj to ADP [about, definitely]
about prep Talk NOUN [patents]
patents pobj about ADP [with]
with prep patents NOUN [GOOG]
GOOG pobj with ADP []
definitely advmod Talk NOUN []
not neg got VERB []
the det treatment NOUN []
treatment nsubj got VERB [the]
got conj is VERB [not, treatment]

不 ,所以 got 它正在定位?

0 回复 | 直到 7 年前

Sofie VL 7 年前

您可以简单地定义和循环找到的否定标记的头标记:

negation_tokens = [tok for tok in doc if tok.dep_ == 'neg']
negation_head_tokens = [token.head for token in negation_tokens]

for token in negation_head_tokens:
    print(token.text, token.dep_, token.head.text, token.head.pos_, [child for child in token.children])

got .