Scribd
Upload
3 views3 pages

NLP Examples

The document provides examples of various Natural Language Processing (NLP) techniques using the NLTK library, including Word Sense Disambiguation (WSD) with the Lesk algorithm, tokenization, stopword removal, stemming, and part-of-speech tagging. Each technique is demonstrated with code snippets and sample sentences to illustrate their functionality. The document also includes instructions for downloading necessary datasets for running the examples.

Uploaded by

ramadevinadipudi5
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views3 pages

NLP Examples

The document provides examples of various Natural Language Processing (NLP) techniques using the NLTK library, including Word Sense Disambiguation (WSD) with the Lesk algorithm, tokenization, stopword removal, stemming, and part-of-speech tagging. Each technique is demonstrated with code snippets and sample sentences to illustrate their functionality. The document also includes instructions for downloading necessary datasets for running the examples.

Uploaded by

ramadevinadipudi5
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

# ==============================

# WORD SENSE DISAMBIGUATION (WSD)


# Example: "plant"
# ==============================

import nltk

# Download required datasets (run once per session in Colab)


[Link]('punkt')
[Link]('wordnet')
[Link]('omw-1.4')

from [Link] import lesk


from [Link] import word_tokenize
from [Link] import wordnet as wn

# Function for WSD


def disambiguate_word(sentence, ambiguous_word):
print("\nSentence:", sentence)

# Tokenize sentence
context = word_tokenize(sentence)

# Apply Lesk algorithm


sense = lesk(context, ambiguous_word)

if sense:
print("Ambiguous Word:", ambiguous_word)
print("Predicted Sense:", [Link]())
print("Definition:", [Link]())
print("Example Usage:", [Link]())
else:
print("No sense found.")

# Example 1 (Plant = living organism)


sentence1 = "She watered the plant in the garden."
disambiguate_word(sentence1, "plant")

print("\n------------------------------------")

# Example 2 (Plant = factory)


sentence2 = "The company built a new plant to manufacture cars."
disambiguate_word(sentence2, "plant")
Tokenization

import nltk
[Link]('punkt')

from [Link] import word_tokenize, sent_tokenize

text = "Natural Language Processing is interesting. It is a branch of AI."

# Sentence Tokenization
sentences = sent_tokenize(text)
print("Sentences:", sentences)

# Word Tokenization
words = word_tokenize(text)
print("Words:", words)

Stopword Removal

import nltk
[Link]('stopwords')
[Link]('punkt')

from [Link] import stopwords


from [Link] import word_tokenize

text = "This is a simple example to demonstrate stopword removal."

stop_words = set([Link]('english'))
words = word_tokenize(text)

filtered_words = [w for w in words if [Link]() not in stop_words]

print("Original Words:", words)


print("After Stopword Removal:", filtered_words)

Stemming Example

import nltk
[Link]('punkt')
from [Link] import PorterStemmer
from [Link] import word_tokenize

stemmer = PorterStemmer()

text = "playing played plays easily fair fairness"


words = word_tokenize(text)

stemmed_words = [[Link](word) for word in words]

print("Stemmed Words:", stemmed_words)

POS Tagging

import nltk

[Link]('punkt')
[Link]('averaged_perceptron_tagger_eng')

import nltk

# Download required resources


[Link]('punkt')
[Link]('averaged_perceptron_tagger_eng')

from [Link] import word_tokenize


from nltk import pos_tag

sentence = "Natural Language Processing is very interesting"

words = word_tokenize(sentence)
tags = pos_tag(words)

print("POS Tags:", tags)

You might also like