使用Python在NLP中的命名实体识别中提取人名

Question

I have a sentence for which i need to identify the Person names alone:

For example:

sentence = "Larry Page is an American business magnate and computer scientist who is the co-founder of Google, alongside Sergey Brin"

I have used the below code to identify the NERs.

from nltk import word_tokenize, pos_tag, ne_chunk
print(ne_chunk(pos_tag(word_tokenize(sentence))))

The output i received was:

(S
  (PERSON Larry/NNP)
  (ORGANIZATION Page/NNP)
  is/VBZ
  an/DT
  (GPE American/JJ)
  business/NN
  magnate/NN
  and/CC
  computer/NN
  scientist/NN
  who/WP
  is/VBZ
  the/DT
  co-founder/NN
  of/IN
  (GPE Google/NNP)
  ,/,
  alongside/RB
  (PERSON Sergey/NNP Brin/NNP))

I want to extract all the person names, such as

Larry Page
Sergey Brin

In order to achieve this, I refereed this link and tried this.

from nltk.tag.stanford import StanfordNERTagger
st = StanfordNERTagger('/usr/share/stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz','/usr/share/stanford-ner/stanford-ner.jar')

However i continue to get this error:

LookupError: Could not find stanford-ner.jar jar file at /usr/share/stanford-ner/stanford-ner.jar

Where can i download this file?

As informed above, the result that i am expecting in the form of list or dictionary is :

Larry Page
Sergey Brin

Answer 1

In Long

Please read these carefully :

• https://stackoverflow.com/a/49345866/610569
• Extract list of Persons and Organizations using Stanford NER Tagger in NLTK

Understand the solution, don't just copy and paste.

---

TL;DR

In terminal:

pip install -U nltk

wget http://nlp.stanford.edu/software/stanford-corenlp-full-2016-10-31.zip
unzip stanford-corenlp-full-2016-10-31.zip && cd stanford-corenlp-full-2016-10-31

java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer \
-preload tokenize,ssplit,pos,lemma,parse,depparse \
-status_port 9000 -port 9000 -timeout 15000

In Python

from nltk.tag.stanford import CoreNLPNERTagger

def get_continuous_chunks(tagged_sent):
    continuous_chunk = []
    current_chunk = []

    for token, tag in tagged_sent:
        if tag != "O":
            current_chunk.append((token, tag))
        else:
            if current_chunk: # if the current chunk is not empty
                continuous_chunk.append(current_chunk)
                current_chunk = []
    # Flush the final current_chunk into the continuous_chunk, if any.
    if current_chunk:
        continuous_chunk.append(current_chunk)
    return continuous_chunk


stner = CoreNLPNERTagger()
tagged_sent = stner.tag('Rami Eid is studying at Stony Brook University in NY'.split())

named_entities = get_continuous_chunks(tagged_sent)
named_entities_str_tag = [(" ".join([token for token, tag in ne]), ne[0][1]) for ne in named_entities]


print(named_entities_str_tag)

[out]:

[('Rami Eid', 'PERSON'), ('Stony Brook University', 'ORGANIZATION'), ('NY', 'LOCATION')]

You might find this help too: Unpacking a list / tuple of pairs into two lists / tuples

Answer 2

In the first place you need to download the jar files and the rest of the necessary files. Follow the link : https://gist.github.com/troyane/c9355a3103ea08679baf . Run the code to download the files(except the last few line). Once done with the downloading part you are now ready to do the extraction part.

from nltk.tag.stanford import StanfordNERTagger
st = StanfordNERTagger('/home/saheli/Downloads/my_project/stanford-ner/english.all.3class.distsim.crf.ser.gz',
                   '/home/saheli/Downloads/my_project/stanford-ner/stanford-ner.jar')