问使用python的stanford-nlp中的回指解析

EN

from pycorenlp import StanfordCoreNLP

nlp = StanfordCoreNLP('http://localhost:9000')


def resolve(corenlp_output):
    """ Transfer the word form of the antecedent to its associated pronominal anaphor(s) """
    for coref in corenlp_output['corefs']:
        mentions = corenlp_output['corefs'][coref]
        antecedent = mentions[0]  # the antecedent is the first mention in the coreference chain
        for j in range(1, len(mentions)):
            mention = mentions[j]
            if mention['type'] == 'PRONOMINAL':
                # get the attributes of the target mention in the corresponding sentence
                target_sentence = mention['sentNum']
                target_token = mention['startIndex'] - 1
                # transfer the antecedent's word form to the appropriate token in the sentence
                corenlp_output['sentences'][target_sentence - 1]['tokens'][target_token]['word'] = antecedent['text']


def print_resolved(corenlp_output):
    """ Print the "resolved" output """
    possessives = ['hers', 'his', 'their', 'theirs']
    for sentence in corenlp_output['sentences']:
        for token in sentence['tokens']:
            output_word = token['word']
            # check lemmas as well as tags for possessive pronouns in case of tagging errors
            if token['lemma'] in possessives or token['pos'] == 'PRP$':
                output_word += "'s"  # add the possessive morpheme
            output_word += token['after']
            print(output_word, end='')


text = "Tom and Jane are good friends. They are cool. He knows a lot of things and so does she. His car is red, but " \
       "hers is blue. It is older than hers. The big cat ate its dinner."

output = nlp.annotate(text, properties= {'annotators':'dcoref','outputFormat':'json','ner.useSUTime':'false'})

resolve(output)

print('Original:', text)
print('Resolved: ', end='')
print_resolved(output)

Original: Tom and Jane are good friends. They are cool. He knows a lot of things and so does she. His car is red, but hers is blue. It is older than hers. The big cat ate his dinner.
Resolved: Tom and Jane are good friends. Tom and Jane are cool. Tom knows a lot of things and so does Jane. Tom's car is red, but Jane's is blue. His car is older than Jane's. The big cat ate The big cat's dinner.

import spacy

nlp = spacy.load('en_coref_md')

doc = nlp(u'Phone area code will be valid only when all the below conditions are met. It cannot be left blank. It should be numeric. It cannot be less than 200. Minimum number of digits should be 3. ')

print(doc._.coref_clusters)

print(doc._.coref_resolved)

from stanfordnlp.server import CoreNLPClient
from nltk import tokenize

client = CoreNLPClient(annotators=['tokenize','ssplit', 'pos', 'lemma', 'ner', 'parse', 'coref'], memory='4G', endpoint='http://localhost:9001')

def pronoun_resolution(text):

    ann = client.annotate(text)
    modified_text = tokenize.sent_tokenize(text)

    for coref in ann.corefChain:

        antecedent = []
        for mention in coref.mention:
            phrase = []
            for i in range(mention.beginIndex, mention.endIndex):
                phrase.append(ann.sentence[mention.sentenceIndex].token[i].word)
            if antecedent == []:
                antecedent = ' '.join(word for word in phrase)
            else:
                anaphor = ' '.join(word for word in phrase)
                modified_text[mention.sentenceIndex] = modified_text[mention.sentenceIndex].replace(anaphor, antecedent)

    modified_text = ' '.join(modified_text)

    return modified_text

text = 'Tom is a smart boy. He knows a lot of things.'
pronoun_resolution(text)