使用Stanford coreNLP的python nltk中的共指消解

Question

斯坦福CoreNLP提供了指代消解这里提到,也是这个线程,这提供了有关其在Java实现的一些见解.

但是,我使用的是python和NLTK,我不知道如何在我的python代码中使用CoreNLP的Coreference解析功能.我已经能够在NLTK中设置StanfordParser,这是我的代码到目前为止.

from nltk.parse.stanford import StanfordDependencyParser
stanford_parser_dir = 'stanford-parser/'
eng_model_path = stanford_parser_dir  + "stanford-parser-models/edu/stanford/nlp/models/lexparser/englishRNN.ser.gz"
my_path_to_models_jar = stanford_parser_dir  + "stanford-parser-3.5.2-models.jar"
my_path_to_jar = stanford_parser_dir  + "stanford-parser.jar"

如何在python中使用CoreNLP的共参分辨率？

Answer 1

正如@Igor所提到的你可以尝试在这个GitHub仓库中实现的python包装器:https://github.com/dasmith/stanford-corenlp-python

这个repo包含两个主要文件:corenlp.py client.py

执行以下更改以使coreNLP正常工作:

1. 在corenlp.py中,更改corenlp文件夹的路径.设置本地计算机包含corenlp文件夹的路径,并在corenlp.py的第144行添加路径

   if not corenlp_path: corenlp_path = <path to the corenlp file>

2. "corenlp.py"中的jar文件版本号不同.根据您拥有的corenlp版本进行设置.在corenlp.py的第135行更改它

   jars = ["stanford-corenlp-3.4.1.jar", "stanford-corenlp-3.4.1-models.jar", "joda-time.jar", "xom.jar", "jollyday.jar"]

在此替换3.4.1与您下载的jar版本.

3. 运行命令:

   python corenlp.py

这将启动一个服务器

4. 现在运行主客户端程序

   python client.py

这提供了一个字典,您可以使用'coref'作为密钥访问coref:

例如:约翰是一名计算机科学家.他喜欢编码.

{
     "coref": [[[["a Computer Scientist", 0, 4, 2, 5], ["John", 0, 0, 0, 1]], [["He", 1, 0, 0, 1], ["John", 0, 0, 0, 1]]]]
}

我在Ubuntu 16.04上试过这个.使用java版本7或8.

Answer 2

斯坦福大学的 CoreNLP 现在有一个名为 StanfordNLP的官方 Python 绑定，您可以在StanfordNLP 网站 中阅读。

原生 API似乎还不支持 coref 处理器，但您可以使用 CoreNLPClient 接口从 Python 调用“标准”CoreNLP（原始 Java 软件）。

因此，按照此处的说明设置 Python 包装器后，您可以获得这样的共引用链：

from stanfordnlp.server import CoreNLPClient

text = 'Barack was born in Hawaii. His wife Michelle was born in Milan. He says that she is very smart.'
print(f"Input text: {text}")

# set up the client
client = CoreNLPClient(properties={'annotators': 'coref', 'coref.algorithm' : 'statistical'}, timeout=60000, memory='16G')

# submit the request to the server
ann = client.annotate(text)    

mychains = list()
chains = ann.corefChain
for chain in chains:
    mychain = list()
    # Loop through every mention of this chain
    for mention in chain.mention:
        # Get the sentence in which this mention is located, and get the words which are part of this mention
        # (we can have more than one word, for example, a mention can be a pronoun like "he", but also a compound noun like "His wife Michelle")
        words_list = ann.sentence[mention.sentenceIndex].token[mention.beginIndex:mention.endIndex]
        #build a string out of the words of this mention
        ment_word = ' '.join([x.word for x in words_list])
        mychain.append(ment_word)
    mychains.append(mychain)

for chain in mychains:
    print(' <-> '.join(chain))

Answer 3

stanfordcorenlp（相对较新的包装器）可能适合您。

假设文本为“ 巴拉克·奥巴马（Barack Obama）出生于夏威夷。他是总统。奥巴马于2008年当选。 ”

代码：

# coding=utf-8

import json
from stanfordcorenlp import StanfordCoreNLP

nlp = StanfordCoreNLP(r'G:\JavaLibraries\stanford-corenlp-full-2017-06-09', quiet=False)
props = {'annotators': 'coref', 'pipelineLanguage': 'en'}

text = 'Barack Obama was born in Hawaii.  He is the president. Obama was elected in 2008.'
result = json.loads(nlp.annotate(text, properties=props))

num, mentions = result['corefs'].items()[0]
for mention in mentions:
    print(mention)

上面的每个“提法”都是这样的Python字典：

{
  "id": 0,
  "text": "Barack Obama",
  "type": "PROPER",
  "number": "SINGULAR",
  "gender": "MALE",
  "animacy": "ANIMATE",
  "startIndex": 1,
  "endIndex": 3,
  "headIndex": 2,
  "sentNum": 1,
  "position": [
    1,
    1
  ],
  "isRepresentativeMention": true
}