Stanford CoreNLP提供了共同参考解决方案Platform as a Service,同时也提供了as mentioned here,this thread,提供了有关其在Java中实现的一些见解。
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的共参考分辨率?
答案 0 :(得分:6)
如@Igor所述你可以尝试在这个GitHub仓库中实现的python包装器:https://github.com/dasmith/stanford-corenlp-python
此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:
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>
“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。
运行命令:
python corenlp.py
这将启动服务器
现在运行主客户端程序
python client.py
这提供了一个字典,你可以使用'coref'作为密钥来访问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.
答案 1 :(得分:3)
stanfordcorenlp,相对较新的包装器,可能适合您。
假设文本是“ Barack Obama出生在夏威夷。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“提及”都是这样的Python词典:
{
"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
}
答案 2 :(得分:1)
也许这适合你? https://github.com/dasmith/stanford-corenlp-python 如果没有,您可以尝试使用http://www.jython.org/
自行合并两者答案 3 :(得分:0)
斯坦福大学的CoreNLP现在有一个名为StanfordNLP的official Python binding,您可以在StanfordNLP website中阅读。
原生API doesn't seem仍支持coref处理器,但是您可以使用CoreNLPClient接口从Python调用“标准” CoreNLP(原始Java软件)。
因此,按照说明设置Python包装器here之后,您可以像这样获得共指链:
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))