python - 使用依赖规则匹配的aspect-opinion提取中的命名实体识别

Question

使用 Spacy，我根据我定义的语法规则从文本中提取方面-意见对。规则基于POS标签和依赖标签，由token.pos_获取和 token.dep_ .下面是语法规则之一的示例。如果我传了句Japan is cool,它返回 [('Japan', 'cool', 0.3182)] ，其中该值代表cool的极性.

但是我不知道如何让它识别命名实体。例如，如果我通过 Air France is cool ，我要得到[('Air France', 'cool', 0.3182)]但我目前得到的是 [('France', 'cool', 0.3182)] .

我检查了 Spacy 在线文档，我知道如何提取 NE( doc.ents )。但我想知道可能的解决方法是使我的提取器工作。请注意，我不想要强制措施，例如连接字符串 AirFrance , Air_France等等。

谢谢!

import spacy

nlp = spacy.load("en_core_web_lg-2.2.5")
review_body = "Air France is cool."
doc=nlp(review_body)

rule3_pairs = []

for token in doc:

    children = token.children
    A = "999999"
    M = "999999"
    add_neg_pfx = False

    for child in children :
        if(child.dep_ == "nsubj" and not child.is_stop): # nsubj is nominal subject
            A = child.text

        if(child.dep_ == "acomp" and not child.is_stop): # acomp is adjectival complement
            M = child.text

        # example - 'this could have been better' -> (this, not better)
        if(child.dep_ == "aux" and child.tag_ == "MD"): # MD is modal auxiliary
            neg_prefix = "not"
            add_neg_pfx = True

        if(child.dep_ == "neg"): # neg is negation
            neg_prefix = child.text
            add_neg_pfx = True

    if (add_neg_pfx and M != "999999"):
        M = neg_prefix + " " + M

    if(A != "999999" and M != "999999"):
        rule3_pairs.append((A, M, sid.polarity_scores(M)['compound']))

结果

rule3_pairs
>>> [('France', 'cool', 0.3182)]

期望输出

rule3_pairs
>>> [('Air France', 'cool', 0.3182)]

Answer 1

在提取器中集成实体非常容易。对于每对 child ，您应该检查“A” child 是否是某个命名实体的头部，如果是，则使用整个实体作为您的对象。

这里我提供整个代码

!python -m spacy download en_core_web_lg
import nltk
nltk.download('vader_lexicon')

import spacy
nlp = spacy.load("en_core_web_lg")

from nltk.sentiment.vader import SentimentIntensityAnalyzer
sid = SentimentIntensityAnalyzer()


def find_sentiment(doc):
    # find roots of all entities in the text
    ner_heads = {ent.root.idx: ent for ent in doc.ents}
    rule3_pairs = []
    for token in doc:
        children = token.children
        A = "999999"
        M = "999999"
        add_neg_pfx = False
        for child in children:
            if(child.dep_ == "nsubj" and not child.is_stop): # nsubj is nominal subject
                if child.idx in ner_heads:
                    A = ner_heads[child.idx].text
                else:
                    A = child.text
            if(child.dep_ == "acomp" and not child.is_stop): # acomp is adjectival complement
                M = child.text
            # example - 'this could have been better' -> (this, not better)
            if(child.dep_ == "aux" and child.tag_ == "MD"): # MD is modal auxiliary
                neg_prefix = "not"
                add_neg_pfx = True
            if(child.dep_ == "neg"): # neg is negation
                neg_prefix = child.text
                add_neg_pfx = True
        if (add_neg_pfx and M != "999999"):
            M = neg_prefix + " " + M
        if(A != "999999" and M != "999999"):
            rule3_pairs.append((A, M, sid.polarity_scores(M)['compound']))
    return rule3_pairs

print(find_sentiment(nlp("Air France is cool.")))
print(find_sentiment(nlp("I think Gabriel García Márquez is not boring.")))
print(find_sentiment(nlp("They say Central African Republic is really great. ")))

此代码的输出将是您所需要的:

[('Air France', 'cool', 0.3182)]
[('Gabriel García Márquez', 'not boring', 0.2411)]
[('Central African Republic', 'great', 0.6249)]

享受!