wordnet lemmatization and pos tagging in python
As in the source code of nltk.corpus.reader.wordnet (http://www.nltk.org/_modules/nltk/corpus/reader/wordnet.html)
#{ Part-of-speech constants
ADJ, ADJ_SAT, ADV, NOUN, VERB = 'a', 's', 'r', 'n', 'v'
#}
POS_LIST = [NOUN, VERB, ADJ, ADV]
Steps to convert : Document->Sentences->Tokens->POS->Lemmas
import nltk
from nltk.stem import WordNetLemmatizer
from nltk.corpus import wordnet
#example text text = 'What can I say about this place. The staff of these restaurants is nice and the eggplant is not bad'
class Splitter(object):
"""
split the document into sentences and tokenize each sentence
"""
def __init__(self):
self.splitter = nltk.data.load('tokenizers/punkt/english.pickle')
self.tokenizer = nltk.tokenize.TreebankWordTokenizer()
def split(self,text):
"""
out : ['What', 'can', 'I', 'say', 'about', 'this', 'place', '.']
"""
# split into single sentence
sentences = self.splitter.tokenize(text)
# tokenization in each sentences
tokens = [self.tokenizer.tokenize(sent) for sent in sentences]
return tokens
class LemmatizationWithPOSTagger(object):
def __init__(self):
pass
def get_wordnet_pos(self,treebank_tag):
"""
return WORDNET POS compliance to WORDENT lemmatization (a,n,r,v)
"""
if treebank_tag.startswith('J'):
return wordnet.ADJ
elif treebank_tag.startswith('V'):
return wordnet.VERB
elif treebank_tag.startswith('N'):
return wordnet.NOUN
elif treebank_tag.startswith('R'):
return wordnet.ADV
else:
# As default pos in lemmatization is Noun
return wordnet.NOUN
def pos_tag(self,tokens):
# find the pos tagginf for each tokens [('What', 'WP'), ('can', 'MD'), ('I', 'PRP') ....
pos_tokens = [nltk.pos_tag(token) for token in tokens]
# lemmatization using pos tagg
# convert into feature set of [('What', 'What', ['WP']), ('can', 'can', ['MD']), ... ie [original WORD, Lemmatized word, POS tag]
pos_tokens = [ [(word, lemmatizer.lemmatize(word,self.get_wordnet_pos(pos_tag)), [pos_tag]) for (word,pos_tag) in pos] for pos in pos_tokens]
return pos_tokens
lemmatizer = WordNetLemmatizer()
splitter = Splitter()
lemmatization_using_pos_tagger = LemmatizationWithPOSTagger()
#step 1 split document into sentence followed by tokenization
tokens = splitter.split(text)
#step 2 lemmatization using pos tagger
lemma_pos_token = lemmatization_using_pos_tagger.pos_tag(tokens)
print(lemma_pos_token)
First of all, you can use nltk.pos_tag()
directly without training it.
The function will load a pretrained tagger from a file. You can see the file name
with nltk.tag._POS_TAGGER
:
nltk.tag._POS_TAGGER
>>> 'taggers/maxent_treebank_pos_tagger/english.pickle'
As it was trained with the Treebank corpus, it also uses the Treebank tag set.
The following function would map the treebank tags to WordNet part of speech names:
from nltk.corpus import wordnet
def get_wordnet_pos(treebank_tag):
if treebank_tag.startswith('J'):
return wordnet.ADJ
elif treebank_tag.startswith('V'):
return wordnet.VERB
elif treebank_tag.startswith('N'):
return wordnet.NOUN
elif treebank_tag.startswith('R'):
return wordnet.ADV
else:
return ''
You can then use the return value with the lemmatizer:
from nltk.stem.wordnet import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
lemmatizer.lemmatize('going', wordnet.VERB)
>>> 'go'
Check the return value before passing it to the Lemmatizer because an empty string would give a KeyError
.