How to install and invoke Stanford NERTagger?

Question

I am trying to use NLTK interface for Stanford NER in the python enviornment, nltk.tag.stanford.NERTagger.

from nltk.tag.stanford import NERTagger
st = NERTagger('/usr/share/stanford-ner/classifiers/all.3class.distsim.crf.ser.gz',
               '/usr/share/stanford-ner/stanford-ner.jar') 
st.tag('Rami Eid is studying at Stony Brook University in NY'.split())

I am supposed to get the output:

[('Rami', 'PERSON'), ('Eid', 'PERSON'), ('is', 'O'), ('studying', 'O'),
('at', 'O'), ('Stony', 'ORGANIZATION'), ('Brook', 'ORGANIZATION'),
('University', 'ORGANIZATION'), ('in', 'O'), ('NY', 'LOCATION')]

I have installed NLTK according the procedure described in the NLTK website. However, I can not find /usr/share/stanford-ner at all. Where and how do I find the whole package and install it in my directory.

See https://gist.github.com/alvations/0ed8641d7d2e1941b9f9 and https://gist.github.com/alvations/e1df0ba227e542955a8a — alvas, Mar 17 '16 at 12:15

score 22 · Answer 1 · answered Aug 08 '16 at 10:26

22

Just thought it would be worth mentioning that the import line is now:

from nltk.tag.stanford import StanfordNERTagger

answered Aug 08 '16 at 10:26

Matthew Frost

578
5
13

score 4 · Answer 2 · answered May 27 '14 at 09:08

4

It might be easier to look at the more recent interfaces to Stanford CoreNLP for python which are available here: http://nlp.stanford.edu/software/corenlp.shtml

answered May 27 '14 at 09:08

Daniel

5,839
9
46
85

4

I found the solution. I have to download the Stanford package independent of the NLKT download, put it in the place the path indicates and change the directory name in the path described in the NLKT document to whatever name I want to use for the directory. I think it would be nice if the NLKT documentation say this explicitly. – Hans May 27 '14 at 19:49
4

I think you should add your solution as an answer, so that later on people use it. – Daniel May 27 '14 at 19:59

score 2 · Answer 3 · edited Mar 18 '16 at 09:17

2

One has to download the Stanford package independent of the NLTK download, put it in the place the path indicates and change the directory name in the path described in the NLTK document to whatever name one wants to use for the directory. It would have been nice if the NLTK documentation would state this explicitly.

edited Mar 18 '16 at 09:17

Rohan Amrute

764
1
9
23

answered Jul 28 '14 at 15:54

Hans

1,269
3
19
38

1

Hi Hans, can you sample your solution if it involves any code or the changes that you made to your code. Thank you – Alekhya Vemavarapu Oct 13 '15 at 05:13

score 2 · Answer 4 · answered Mar 17 '16 at 12:16

Although this is a link only answer, it will resolve the OP's question.

For Windows: https://gist.github.com/alvations/0ed8641d7d2e1941b9f9

For Linux: https://gist.github.com/alvations/e1df0ba227e542955a8a

EDITED

But do note that this is not an eternal solution and since Stanford NLP tools and NLTK changes more than 2-3 times a year, please check the https://github.com/nltk/nltk/wiki/Installing-Third-Party-Software for latest setup instructions for NLTK API to Stanford tools.

Solutions above are posted on 17.03.2016

score 2 · Answer 5 · answered Aug 09 '17 at 11:28

2

from nltk.tag.stanford import StanfordNERTagger
st = StanfordNERTagger('/Users/mahendrabilagi/Desktop/stanford-ner-2017-06-09/classifiers/english.all.3class.distsim.crf.ser.gz',
           '/Users/mahendrabilagi/Desktop/stanford-ner-2017-06-09/stanford-ner.jar')
print st.tag('Rami Eid is studying at Stony Brook University in Bengaluru'.split())

answered Aug 09 '17 at 11:28

Mahendra Bilagi

51
9

from where i can download these files – Talha Anwar Sep 07 '20 at 14:35

How to install and invoke Stanford NERTagger?

5 Answers5

EDITED

Linked

Related