NLP | Extracting Named Entities
Recognizing named entity is a specific kind of chunk extraction that uses entity tags along with chunk tags.
Common entity tags include PERSON, LOCATION and ORGANIZATION. POS tagged sentences are parsed into chunk trees with normal chunking but the trees labels can be entity tags in place of chunk phrase tags. NLTK has already a pre-trained named entity chunker which can be used using
ne_chunk() method in the nltk.chunk module. This method chunks a single sentence into a Tree.
Code #1 : Using ne-chunk() on tagged sentence of the treebank_chunk corpus
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. And to begin with your Machine Learning Journey, join the Machine Learning - Basic Level Course
Tree('S', [Tree('PERSON', [('Pierre', 'NNP')]), Tree('ORGANIZATION', [('Vinken', 'NNP')]), (', ', ', '), ('61', 'CD'), ('years', 'NNS'), ('old', 'JJ'), (', ', ', '), ('will', 'MD'), ('join', 'VB'), ('the', 'DT'), ('board', 'NN'), ('as', 'IN'), ('a', 'DT'), ('nonexecutive', 'JJ'), ('director', 'NN'), ('Nov.', 'NNP'), ('29', 'CD'), ('.', '.')])
two entity tags are found: PERSON and ORGANIZATION. Each of these subtrees contains a list of the words that are recognized as a PERSON or ORGANIZATION.
Code #2 : Method to extract named entites using leaves of all the subtrees
Code #3 : using method to get all the PERSON or ORGANIZATION leaves from a tree
Named entities of PERSON : [[('Pierre', 'NNP')]] Named entites of ORGANIZATION : [[('Vinken', 'NNP')]]
To process multiple sentences at a time,
chunk_ne_sents() is used. In the code below, first 10 sentences from
treebank_chunk.tagged_sents() are processed to get ORGANIZATION
Code #4 : Let’s understand
[[[('Vinken', 'NNP')]], [[('Elsevier', 'NNP')]], [[('Consolidated', 'NNP'), ('Gold', 'NNP'), ('Fields', 'NNP')]], , , [[('Inc.', 'NNP')], [('Micronite', 'NN')]], [[('New', 'NNP'), ('England', 'NNP'), ('Journal', 'NNP')]], [[('Lorillard', 'NNP')]], , ]