NLP | Named Entity Chunker Training

Last Updated : 26 Feb, 2019

Self Named entity chunker can be trained using the ieer corpus, which stands for Information Extraction: Entity Recognition. The ieer corpus has chunk trees but no part-of-speech tags for the words, so it is a bit tedious job to perform.

Named entity chunk trees can be created from ieer corpus using the ieertree2conlltags() and ieer_chunked_sents() functions. This can be used to train the ClassifierChunker class created in the Classification-based chunking.

Code #1 : ieertree2conlltags()

import nltk.tag 
from nltk.chunk.util import conlltags2tree 
from nltk.corpus import ieer 
  
def ieertree2conlltags(tree, tag = nltk.tag.pos_tag): 
    words, ents = zip(*tree.pos()) 
    iobs = [] 
    prev = None
    for ent in ents: 
        if ent == tree.label(): 
            iobs.append('O') 
            prev = None
        elif prev == ent: 
            iobs.append('I-% s' % ent) 
        else: 
            iobs.append('B-% s' % ent) 
            prev = ent 
      
    words, tags = zip(*tag(words)) 
      
    return zip(words, tags, iobs) 

Code #2 : ieer_chunked_sents()

import nltk.tag 
from nltk.chunk.util import conlltags2tree 
from nltk.corpus import ieer 
  
def ieer_chunked_sents(tag = nltk.tag.pos_tag): 
    for doc in ieer.parsed_docs(): 
        tagged = ieertree2conlltags(doc.text, tag) 
        yield conlltags2tree(tagged) 

Using 80 out of 94 sentences for training and the remaining ones for testing.

Code #3 : How the classifier works on the first sentence of the treebank_chunk corpus.

from nltk.corpus import ieer 
from chunkers import ieer_chunked_sents, ClassifierChunker 
from nltk.corpus import treebank_chunk 
  
ieer_chunks = list(ieer_chunked_sents()) 
  
print ("Length of ieer_chunks : ", len(ieer_chunks)) 
  
# initializing chunker 
chunker = ClassifierChunker(ieer_chunks[:80]) 
print("\nparsing : \n", chunker.parse( 
        treebank_chunk.tagged_sents()[0])) 
  
# evaluating 
score = chunker.evaluate(ieer_chunks[80:]) 
  
a = score.accuracy() 
p = score.precision() 
r = score.recall() 
  
print ("\nAccuracy : ", a) 
print ("\nPrecision : ", p) 
print ("\nRecall : ", r) 

Output :

Length of ieer_chunks : 94

parsing : 
Tree('S', [Tree('LOCATION', [('Pierre', 'NNP'), ('Vinken', 'NNP')]),
(', ', ', '), Tree('DURATION', [('61', 'CD'), ('years', 'NNS')]),
Tree('MEASURE', [('old', 'JJ')]), (', ', ', '), ('will', 'MD'), ('join', 'VB'), 
('the', 'DT'), ('board', 'NN'), ('as', 'IN'), ('a', 'DT'), ('nonexecutive', 'JJ'),
('director', 'NN'), Tree('DATE', [('Nov.', 'NNP'), ('29', 'CD')]), ('.', '.')])

Accuracy : 0.8829018388070625

Precision : 0.4088717454194793

Recall : 0.5053635280095352

How it works ?
The ieer trees generated by ieer_chunked_sents() are not entirely accurate. There are no explicit sentence breaks, so each document is a single tree. Also, the words are not explicitly tagged, it’s guess work using nltk.tag.pos_tag().

Attention geek! Strengthen your foundations with the Python Programming Foundation Course and learn the basics.

To begin with, your interview preparations Enhance your Data Structures concepts with the Python DS Course.

My Personal Notes

Related Articles