{"id":25188,"date":"2018-08-20T04:17:46","date_gmt":"2018-08-20T04:17:46","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=25188"},"modified":"2026-04-29T11:37:20","modified_gmt":"2026-04-29T06:07:20","slug":"nltk-python-tutorial","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/nltk-python-tutorial\/","title":{"rendered":"NLTK(Natural Language Toolkit) Python Tutorial"},"content":{"rendered":"

In our last session, we discussed the NLP Tutorial<\/strong>. Today, in this NLTK Python<\/strong> Tutorial, we will learn to perform Natural Language Processing with NLTK. We will perform tasks like NLTK tokenize, removing stop words, stemming NLTK, lemmatization NLTK, finding synonyms and antonyms, and more.<\/span><\/p>\n

So, let’s start the NLTK Python Tutorial.<\/p>\n

What is NLTK?<\/h3>\n

The Natural Language Toolkit (NLTK) is a Python library used in NLP projects. It is one of the oldest and most used libraries for text processing. NLTK has everything you need to work with human language \u2013 like breaking text into words, tagging parts of speech, and understanding sentence structure. It helps make machines understand human communication.<\/p>\n

First getting to see the light in 2001, NLTK hopes to support research and teaching in NLP and other areas closely related. These include Artificial Intelligence<\/strong>, empirical linguistics, cognitive science, information retrieval, and Machine Learning<\/strong>.<\/span><\/p>\n

How to Install NLTK?<\/h3>\n

To install NLTK, you can use Python pip-<\/span><\/p>\n

pip install nltk<\/pre>\n
Then, to import it, you can type in the interpreter-<\/p>\n
>>> import nltk<\/pre>\n
Finally, to install packages from NLTK, you need to use its downloader. Try this-<\/p>\n
>>> nltk.download()<\/pre>\n
\"NLTK<\/a>
NLTK Python Tutorial – How to Install NLTK?<\/p><\/div>\n
You can download all packages or choose the ones you wish to download. Explore the \u2018All Packages\u2019 tab.<\/span><\/p>\n
Tokenize Text using NLTK in Python<\/h3>\n
Before processing the text in the NLTK Python, you should tokenize it. What we mean is you should split it into smaller parts- paragraphs to sentences, sentences to words. We have two kinds of tokenizers- for sentences and for words.<\/span><\/p>\n
a. NLTK Sentence Tokenizer<\/h4>\n
Let\u2019s try tokenizing a sentence.<\/span><\/p>\n
>>> text=\"Today is a great day. It is even better than yesterday. And yesterday was the best day ever.\"\r\n>>> from nltk.tokenize import sent_tokenize\r\n>>> sent_tokenize(text)<\/pre>\n
[‘Today is a great day.’, ‘It is even better than yesterday.’, ‘And yesterday was the best day ever.’]<\/strong>
\nLet\u2019s try another? We\u2019ll use an exchange of dialogue this time.<\/span><\/p>\n
>>> sent_tokenize(\"Hi, how are you? I'm good, you? Great!\")<\/pre>\n
[‘Hi, how are you?’, “I’m good, you?”, ‘Great!’]<\/strong>
\nOkay, one more in the NLTK Python Tutorial. How about we use words like Mrs. and Martinez\u2019s in the text? Will the tokenizer be able to catch it?<\/span><\/p>\n
>>> nltk.sent_tokenize(\"Last night, I went to Mrs. Martinez's housewarming. It was a disaster.\")<\/pre>\n
[“Last night, I went to Mrs. Martinez’s housewarming.”, ‘It was a disaster.’]<\/strong><\/p>\n