python - 使用 SpaCy 解析句子的更好方法？

Question

我正在使用 SpaCy 查找包含以代词作为主语的“is”或“was”的句子，并返回句子的宾语。我的代码有效，但我觉得必须有更好的方法来做到这一点。

import spacy
nlp = spacy.load('en_core_web_sm')

ex_phrase = nlp("He was a genius. I really liked working with him. He is a dog owner. She is very kind to animals.")


#create an empty list to hold any instance of this particular construction
list_of_responses = []

#split into sentences
for sent in ex_phrase.sents:
    for token in sent:
        #check to see if the word 'was' or 'is' is in each sentence, if so, make a list of the verb's constituents
        if token.text == 'was' or token.text == 'is':
            dependency = [child for child in token.children]
            #if the first constituent is a pronoun, make sent_object equal to the item at index 1 in the list of constituents
            if dependency[0].pos_ == 'PRON':
                sent_object = dependency[1]

    #create a string of the entire object of the verb. For instance, if sent_object = 'genius', this would create a string 'a genius'
    for token in sent:
        if token == sent_object:
            whole_constituent = [t.text for t in token.subtree]
            whole_constituent = " ".join(whole_constituent)

    #check to see what the pronoun was, and depending on if it was 'he' or 'she', construct a coherent followup sentence
    if dependency[0].text.lower() == 'he':
        returning_phrase = f"Why do you think him being {whole_constituent} helped the two of you get along?"
    elif dependency[0].text.lower() == 'she':
        returning_phrase = f"Why do you think her being {whole_constituent} helped the two of you get along?"

    #add each followup sentence to the list. For some reason it creates a lot of duplicates, so I have to use set
    list_of_responses.append(returning_phrase)
    list_of_responses = list(set(list_of_responses))

标签： pythonnlpspacy

Answer 1

您的代码似乎正在尝试做一些比您在问题中描述的更复杂的事情。我试图用你的代码做你想做的事情。获取动词“is”或“was”的宾语/属性只是其中的一部分。

import spacy
from pprint import pprint

nlp = spacy.load('en')

text = "He was a genius. I really liked working with him. He is a dog owner. She is very kind to animals."

def get_pro_nsubj(token):
    # get the (lowercased) subject pronoun if there is one
    return [child.lower_ for child in token.children if child.dep_ == 'nsubj'][0]

list_of_responses = []

# a mapping of subject to object pronouns
subj_obj_pro_map = {'he': 'him',
                    'she': 'her'
                    }

for token in nlp(text):
    if token.pos_ in ['NOUN', 'ADJ']:
        if token.dep_ in ['attr', 'acomp'] and token.head.lower_ in ['is', 'was']:
            # to test for lemma 'be' use token.head.lemma_ == 'be'
            nsubj = get_pro_nsubj(token.head)
            if nsubj in ['he', 'she']:
                # get the text of each token in the constituent and join it all together
                whole_constituent = ' '.join([t.text for t in token.subtree])
                obj_pro = subj_obj_pro_map[nsubj] # convert subject to object pronoun
                returning_phrase = 'Why do you think {} being {} helped the two of you get along?'.format(obj_pro, whole_constituent)
                list_of_responses.append(returning_phrase)

pprint(list_of_responses)

哪个输出：

['Why do you think him being a genius helped the two of you get along?',
 'Why do you think him being a dog owner helped the two of you get along?',
 'Why do you think her being very kind to animals helped the two of you get '
 'along?']