Skip to content
Related Articles

Related Articles

NLP | Chunking Rules

View Discussion
Improve Article
Save Article
  • Difficulty Level : Easy
  • Last Updated : 29 Jul, 2021
View Discussion
Improve Article
Save Article

Below are the steps involved for Chunking – 
 

  • Conversion of sentence to a flat tree. 
     

  • Creation of Chunk string using this tree.
  • Creation of RegexpChunkParser by parsing the grammar using RegexpParser.
  • Applying the created chunk rule to the ChunkString that matches the sentence into a chunk. 
     

 

  • Splitting the bigger chunk to a smaller chunk using the defined chunk rules. 
     

  • ChunkString is then converted back to tree, with two chunk subtrees. 
     

Code #1: ChunkString getting modified by applying each rule. 
 

Python3




# Loading Libraries
from nltk.chunk.regexp import ChunkString, ChunkRule, ChinkRule
from nltk.tree import Tree
  
# ChunkString() starts with the flat tree
tree = Tree('S', [('the', 'DT'), ('book', 'NN'),
               ('has', 'VBZ'), ('many', 'JJ'), ('chapters', 'NNS')])
  
# Initializing ChunkString()
chunk_string = ChunkString(tree)
print ("Chunk String : ", chunk_string)
  
# Initializing ChunkRule
chunk_rule = ChunkRule('<DT><NN.*><.*>*<NN.*>', 'chunk determiners and nouns')
chunk_rule.apply(chunk_string)
print ("\nApplied ChunkRule : ", chunk_string)
  
# Another ChinkRule
ir = ChinkRule('<VB.*>', 'chink verbs')
ir.apply(chunk_string)
print ("\nApplied ChinkRule : ", chunk_string, "\n")
  
# Back to chunk sub-tree
chunk_string.to_chunkstruct()

Output: 
 

Chunk String :   <<DT>  <NN>  <VBZ>  <JJ>  <NNS> 

Applied ChunkRule :  {<DT>  <NN>  <VBZ>  <JJ>  <NNS>}

Applied ChinkRule :  {<DT>  <NN>} <VBZ> {<JJ>  <NNS>} 

Tree('S', [Tree('CHUNK', [('the', 'DT'), ('book', 'NN')]), 
    ('has', 'VBZ'), Tree('CHUNK', [('many', 'JJ'), ('chapters', 'NNS')])])

Note: This code works exactly in the same manner as explained in the ChunkRule steps above. 
  
Code #2: How to this task directly with RegexpChunkParser. 
 

Python3




# Loading Libraries
from nltk.chunk.regexp import ChunkString, ChunkRule, ChinkRule
from nltk.tree import Tree
from nltk.chunk import RegexpChunkParser
  
# ChunkString() starts with the flat tree
tree = Tree('S', [('the', 'DT'), ('book', 'NN'),
               ('has', 'VBZ'), ('many', 'JJ'), ('chapters', 'NNS')])
  
# Initializing ChunkRule
chunk_rule = ChunkRule('<DT><NN.*><.*>*<NN.*>', 'chunk determiners and nouns')
  
  
# Another ChinkRule
chink_rule = ChinkRule('<VB.*>', 'chink verbs')
  
# Applying RegexpChunkParser
chunker = RegexpChunkParser([chunk_rule, chink_rule])
chunker.parse(tree)

Output: 
 

Tree('S', [Tree('CHUNK', [('the', 'DT'), ('book', 'NN')]), 
    ('has', 'VBZ'), Tree('CHUNK', [('many', 'JJ'), ('chapters', 'NNS')])])

  
Code #3 : Parsing with different ChunkType. 
 

Python3




# Loading Libraries
from nltk.chunk.regexp import ChunkString, ChunkRule, ChinkRule
from nltk.tree import Tree
from nltk.chunk import RegexpChunkParser
  
# ChunkString() starts with the flat tree
tree = Tree('S', [('the', 'DT'), ('book', 'NN'),
               ('has', 'VBZ'), ('many', 'JJ'), ('chapters', 'NNS')])
  
# Initializing ChunkRule
chunk_rule = ChunkRule('<DT><NN.*><.*>*<NN.*>', 'chunk determiners and nouns')
  
  
# Another ChinkRule
chink_rule = ChinkRule('<VB.*>', 'chink verbs')
  
# Applying RegexpChunkParser
chunker = RegexpChunkParser([chunk_rule, chink_rule], chunk_label ='CP')
chunker.parse(tree)

Output: 
 

Tree('S', [Tree('CP', [('the', 'DT'), ('book', 'NN')]), ('has', 'VBZ'), 
          Tree('CP', [('many', 'JJ'), ('chapters', 'NNS')])])

 


My Personal Notes arrow_drop_up
Recommended Articles
Page :

Start Your Coding Journey Now!