从多主语被动句中提取实体

Question

使用Python，我试图从多个主语被动语态句中提取实体。

“约翰和珍妮被大卫指控犯罪”

我的意图是从句子中抽取“约翰和珍妮”作为nsubjpass和_.ent__。

然而，我只能将“John”提取为nsubjpass。

如何把它们都提取出来？

注意，虽然在.ents中发现John是一个实体，但Jenny被认为是conj而不是nsubjpass。如何改进？

代码

each_sentence3 =  "John and Jenny were accused of crimes by David"
doc=nlp(each_sentence3)

passive_toks=[tok for tok in doc if (tok.dep_ == "nsubjpass") ]
if passive_toks != []:
    print(passive_toks)

结果：

[John]

实体清单显示：

代码

`

print(list(doc.ents)

结果

[John, Jenny, David]

现在，如果我们检查整个句子，我们看到如下：

代码：

for tok in doc:   
        print(tok, tok.dep_)

结果

John nsubjpass
and cc
Jenny conj
were auxpass
accused ROOT
of prep
crimes pobj
by agent
David pobj

注意，第二个被动主语Jenny在Spacy中被识别为conj，而不是nsubjpass。

Answer 1

下面是一个使用POS标记和依赖分析来提取主题及其所有连接的示例。

还有一个Token.conjuncts属性，但是它只能直接连接到令牌。请参阅https://github.com/explosion/spaCy/issues/795

each_sentence3 = "John and Jenny were accused of crimes by David"
sent = nlp(each_sentence3)

result = []
subj = None
for word in sent:
    if 'subj' in word.dep_:
        subj = word
        result.append(word)
    elif word.dep_ == 'conj' and word.head == subj:
        result.append(word)
print str(result)


[John, Jenny]