Deploy Python Apps & Docs For Free

A new platform is looking for Alpha testers. Sign up, it's free!

The Fundamentals of Natural Language Processing: A Beginner's Guide

The Fundamentals of Natural Language Processing: A Beginner's Guide

Feb. 11, 2023 by Avi Kumar Talaviya


Natural Language Processing (NLP) is a subfield of machine learning which leverages analysis, generation, and understanding of human languages to derive meaningful insights.

NLP is becoming popular as Large Language Models (LLMs) are growing and used widely in the market. Having foundational knowledge of NLP concepts and techniques can help you become an NLP data scientist, NLP engineer, or distinguished ML engineer to stand out in the job market.

In this article, we will look at some of the NLP techniques you should master as a data scientist:

Table of contents:

  1. Text pre-processing
  2. Text feature extraction
  3. Text sort
  4. Named entity recognition
  5. Parts-of-speech tagging
  6. Text generation
  7. Text-to-speech and speech-to-text techniques
  8. Conclusion

Text pre-processing

Pre-processing techniques such as tokenization, stemming, and lemmatization, help convert raw text into a format that can be easily analyzed.


The fundamental concept in NLP is tokenization. It is the process of breaking down a complex piece of text into smaller units called tokens.

Let’s look at the below code to tokenize the given sentence using the NLTK library.

import nltk

# take a sample text for generating tokens
text = "This is an example of tokenization in NLP tasks."
tokens = nltk.word_tokenize(text)
>>> ['This', 'is', 'an', 'example', 'of', 'tokenization', 'in', 'NLP', 'tasks', '.']


Stemming is the process of reducing words to their base or root form. This can be useful in classification or information retrieval tasks

The below code demonstrates stemming using the PorteStemmer method of the NLTK library.

import nltk
from nltk.stem import PorterStemmer

# create stemmer object using PorterStemmer method of nltk library
stemmer = PorterStemmer()
words = ["run", "runner", "ran", "runs", "easily", "fairly"]
stemmed_words = [stemmer.stem(word) for word in words]
>>> ['run', 'runner', 'ran', 'run', 'easili', 'fairli']


Lemmatization is the process of reducing a word to its base or root form, which is known as the lemma. It is a more sophisticated version of stemming, as it takes into account the context and the part of speech of the word.

Here is an example of lemmatization using the WordNetLemmatizer class from the NLTK library in Python:

import nltk
from nltk.stem import WordNetLemmatizer

# Download the wordnet package'wordnet')

# Define the word to be lemmatized
word = "running"

# Create an instance of the WordNetLemmatizer
lemmatizer = WordNetLemmatizer()

# Lemmatize the word
lemma = lemmatizer.lemmatize(word, pos='v')
>>> run

Text feature extraction

Techniques such as Vocabulary/bag-of-words, n-grams, count vectorization, and word embeddings are used to represent text as numerical features in machine learning models.

Vocabulary or Bag-of-Words

Vocabulary in NLP refers to the set of unique words or tokens in a given text or corpus.

Here is an example of creating a vocabulary in Python using the NLTK library:

import nltk
from nltk.tokenize import word_tokenize

# Tokenize the text
text = "This is an example of building a vocabulary for NLP tasks."
words = word_tokenize(text)

# Create a vocabulary
vocab = set(words)
>>> {'is', 'example', 'building', '.', 'tasks', 
'NLP', 'This', 'an', 'a', 'for', 'vocabulary', 'of'}


An n-gram is a contiguous sequence of n items from a given sample of text or speech, where n can be any positive integer. In NLP, n-grams are often used to capture the context of words in a text.

Here is an example of creating n-grams in Python using the NLTK library:

import nltk
from nltk.util import ngrams

# Tokenize the text
text = "This is an example of creating n-grams."
words = nltk.word_tokenize(text)

# Create bigrams
bigrams = ngrams(words, 2)

# Create trigrams
trigrams = ngrams(words, 3)
>>> [('This', 'is'), ('is', 'an'), ('an', 'example'), ('example', 'of'), ('of', 'creating'), 
('creating', 'n-grams'), 
('n-grams', '.')]
[('This', 'is', 'an'), ('is', 'an', 'example'), ('an', 'example', 'of'), 
('example', 'of', 'creating'), 
('of', 'creating', 'n-grams'), 
('creating', 'n-grams', '.')]

Count vectorization

Text vectorization is the process of converting text data into numerical vectors, which can be used as input for machine learning models. One of the most common techniques for text vectorization is bag-of-words, which represents text as a bag (or multiset) of its words, disregarding grammar and word order but keeping track of the number of occurrences of each word.

Here is an example of text vectorization using the bag-of-words approach in Python using the CountVectorizer class from the sklearn library:

from sklearn.feature_extraction.text import CountVectorizer

# Define the text data
text_data = ["This is a positive sentence.", 
             "This is a negative sentence.", 
             "Another positive sentence."]

# Create an instance of the CountVectorizer
vectorizer = CountVectorizer()

# Fit the vectorizer on the text data

# Transform the text data into numerical vectors
vectors = vectorizer.transform(text_data)
>>> [[0 1 0 1 1 1]
 [0 1 1 0 1 1]
 [1 0 0 1 1 0]]

Text sort

Techniques for classifying text into predefined categories, such as sentiment analysis and spam detection.

Text sorting is one of the most important NLP tasks that involves assigning predefined categories or labels to a given piece of text.

An example of text classification in Python using the scikit-learn library is:

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline

data = fetch_20newsgroups()

model = make_pipeline(TfidfVectorizer(), MultinomialNB()),

labels = model.predict(["This is some example text"])
>>> [11]

In this example, we use 20newsgroups data, which contains nearly 19,000 newsgroup documents, partitioned nearly evenly across 20 different newsgroups. The pipeline vectorizes the text using TfidfVectorizer, then trains a Naive Bayes classifier using the vectorized data and returns the predicted label.

Named entity recognition

Named entity recognition are techniques for identifying and extracting named entities from text, such as people, organizations, and locations.

An entity can be thought of as a category type present in a given text. For example, the name of a certain personality, the name of an organization, location, etc.

Here is a code example to explain Named entity recognition: 

import spacy

# Load the spaCy model for named entity recognition
nlp = spacy.load("en_core_web_sm")

# Define a sample text
text = "Apple is looking at buying U.K. startup for $1 billion"

# Process the text with spaCy
doc = nlp(text)

# Iterate over the entities in the text and print them
for ent in doc.ents:
    print(ent.text, ent.label_)
>>> Apple ORG
$1 billion MONEY

Part-of-speech tagging

Part-of-speech tagging are approaches for identifying the parts of speech of words in a sentence, such as nouns, verbs, and adjectives.

NLTK library of python has a method called ‘pos_tag’ which allows tagging parts of speech with just one line of code.

Let’s take a code example of POS tagging using python:

import nltk

def sentense_pos_tagger(text):
    # tokenize the text
    sample = word_tokenize(text)
    tags = nltk.pos_tag(sample)
    return tags

>>>[('i', 'NN'),
 ('read', 'VBP'),
 ('them', 'PRP'),
 ('in', 'IN'),
 ('change', 'NN'),
 ('in', 'IN'),
 ('meaning', 'VBG'),
 ('the', 'DT'),
 ('history', 'NN'),
 ('of', 'IN'),
 ('slavery', 'NN')]

Text generation

Techniques for generating new text based on a given input, such as machine translation and text summarization.

Text generation is the task of automatically producing new text based on a given input or model. It is a popular area of research in Natural Language Processing (NLP) and has numerous applications such as chatbots, content creation, and language translation.

There are several techniques for text generation, including:

  1. Markov Chain: A statistical model that predicts the next word based on the probability distribution of the previous words in the text. It generates new text by starting with an initial state, and then repeatedly sampling the next word based on the probability distribution learned from the input text.
  2. Sequence-to-Sequence (Seq2Seq) Model: A deep learning model that consists of two recurrent neural networks (RNNs), an encoder, and a decoder. The encoder takes the input text and produces a fixed-length vector representation, while the decoder generates the output text based on the vector representation.
  3. Generative Adversarial Network (GAN): A deep learning model that consists of two neural networks, a generator, and a discriminator. The generator produces new text samples, while the discriminator tries to distinguish between the generated text and the real text. The two networks are trained in an adversarial manner, where the generator tries to produce more realistic text, while the discriminator tries to become better at recognizing fake text.
  4. Transformer-based Models: Transformer models are a type of neural network architecture designed for NLP tasks, such as text classification and machine translation. They have been shown to perform well on text-generation tasks as well.

Text-to-Speech and Speech-to-Text

Techniques for converting speech to text and text to speech.

Text-to-Speech (TTS) and Speech-to-Text (STT) are two important applications of Natural Language Processing (NLP).

  1. Text-to-Speech (TTS): TTS is a technology that allows computers to generate human-like speech from written text. The goal of TTS is to produce speech that is natural, expressive, and matches the intonation, rhythm, and prosody of human speech as closely as possible. TTS systems typically consist of two components: a text analysis module that analyzes the input text, and a speech synthesis module that converts the analyzed text into speech.
  2. Speech-to-Text (STT): STT is a technology that allows computers to transcribe spoken words into written text. STT systems are used in a wide range of applications, including voice-controlled virtual assistants, dictation software, and automatic speech recognition (ASR) systems. STT systems typically use acoustic models and language models to transcribe speech into text.

There are other advanced concepts like Attention-based models, Transformers, and BERT which are widely used in various NLP tasks. Attention-based models and transformers are bringing a new paradigm in the world of technology and artificial intelligence. The latest AI models like GPT 3, GPT 3.5, Dall-E2, Midjourny, and StableDiffusion are leading the wave of generative AI in general, and in particular generative text-based applications like ChatGPT are increasingly popular.


Text-based data is everywhere and businesses of all sizes generate tons of it. To analyze, interpret and gain meaningful full insights out of raw text data, beginner data scientists must learn NLP techniques to succeed in their careers.

To learn NLP techniques and concepts in-depth make sure you check out these recommended courses on DataKwery.