In this blog, we will learn about the different type of text summarization methods and at the end, we will see a practical of the same.
We all interact with applications that use text summarization. several of these applications are for the platform that publishes articles on daily news, amusement, sports. With our busy schedule, we have a tendency to choose to read the summary of this article before we decide to jump in for reading the whole article. Reading a summary help us to spot the interest space, provides a quick context of the story.

Summarization can be defined as a task of producing a concise and fluent summary while preserving key information and overall meaning.
There are many techniques available to generate extractive summarization. To keep it simple, I will be using an unsupervised learning approach to find the sentences similarity and rank them. One benefit of this will be, you don’t need to train and build a model prior start using it for your project.
It’s good to understand Cosine similarity to make the best use of the code you are going to see. Cosine similarity is a measure of similarity between two non-zero vectors of an inner product space that measures the cosine of the angle between them. Its measures cosine of the angle between vectors. The angle will be 0 if sentences are similar.
That’s good for it I think 🙂
How does Text summarization work
Text summarization can broadly be divided into two categories — Extractive Summarization and Abstractive Summarization.
- Extractive Summarization: These methods rely on extracting several parts, such as phrases and sentences, from a piece of text and stack them together to create a summary. Therefore, identifying the right sentences for summarization is of utmost importance in an extractive method.
- Abstractive Summarization: Abstractive methods select words based on semantic understanding, even those words did not appear in the source documents. It aims at producing important material in a new way. They interpret and examine the text using advanced natural language techniques in order to generate a new shorter text that conveys the most critical information from the original text.
It can be correlated to the way human reads a text article or blog post and then summarizes in their own word.
Input document → understands context → semantics → create own summary.
In this article, we will be focusing on the extractive summarization technique.
Next, Below is our code flow to generate summarize text:
Input article → split into sentences → remove stop words → build a similarity matrix → generate rank based on matrix → pick top N sentences for the summary.
Let’s create these methods.
1. Import all necessary libraries
from nltk.cluster.util import cosine_distance
from nltk.corpus import stopwords
import numpy as np
import networkx as nx
2. Generate clean sentences
def read_article(file_name):
file = open(file_name, "r")
filedata = file.readlines()
article = filedata[0].split(". ")
sentences = []
for sentence in article:
print(sentence)
sentences.append(sentence.replace("[^a-zA-Z]", " ").split(" "))
sentences.pop()
return sentences
3. Similarity matrix
This is where we will be using cosine similarity to find similarity between sentences.
def sentence_similarity(sent1, sent2, stopwords=None):
if stopwords is None:
stopwords = []
sent1 = [w.lower() for w in sent1]
sent2 = [w.lower() for w in sent2]
all_words = list(set(sent1 + sent2))
vector1 = [0] * len(all_words)
vector2 = [0] * len(all_words)
# build the vector for the first sentence
for w in sent1:
if w in stopwords:
continue
vector1[all_words.index(w)] += 1
# build the vector for the second sentence
for w in sent2:
if w in stopwords:
continue
vector2[all_words.index(w)] += 1
return 1 - cosine_distance(vector1, vector2)
def build_similarity_matrix(sentences, stop_words):
# Create an empty similarity matrix
similarity_matrix = np.zeros((len(sentences), len(sentences)))
for idx1 in range(len(sentences)):
for idx2 in range(len(sentences)):
if idx1 == idx2: #ignore if both are same sentences
continue
similarity_matrix[idx1][idx2] = sentence_similarity(sentences[idx1], sentences[idx2], stop_words)
return similarity_matrix
4. Generate Summary Method
The method will keep calling all other helper function to keep our summarization pipeline going. Make sure to take a look at all # Steps
in below code.
def generate_summary(file_name, top_n=5):
stop_words = stopwords.words('english')
summarize_text = []
# Step 1 - Read text and tokenize
sentences = read_article(file_name)
# Step 2 - Generate Similary Martix across sentences
sentence_similarity_martix = build_similarity_matrix(sentences, stop_words)
# Step 3 - Rank sentences in similarity martix
sentence_similarity_graph = nx.from_numpy_array(sentence_similarity_martix)
scores = nx.pagerank(sentence_similarity_graph)
# Step 4 - Sort the rank and pick top sentences
ranked_sentence = sorted(((scores[i],s) for i,s in enumerate(sentences)), reverse=True)
print("Indexes of top ranked_sentence order are ", ranked_sentence)
for i in range(top_n):
summarize_text.append(" ".join(ranked_sentence[i][1]))
# Step 5 - Offcourse, output the summarize texr
print("Summarize Text: \n", ". ".join(summarize_text))
Let’s look at it in action.
The complete text from an article titled Microsoft Launches Intelligent Cloud Hub To Upskill Students In AI & Cloud Technologies
In an attempt to build an AI-ready workforce, Microsoft announced Intelligent Cloud Hub which has been launched to empower the next generation of students with AI-ready skills. Envisioned as a three-year collaborative program, Intelligent Cloud Hub will support around 100 institutions with AI infrastructure, course content and curriculum, developer support, development tools and give students access to cloud and AI services. As part of the program, the Redmond giant which wants to expand its reach and is planning to build a strong developer ecosystem in India with the program will set up the core AI infrastructure and IoT Hub for the selected campuses. The company will provide AI development tools and Azure AI services such as Microsoft Cognitive Services, Bot Services and Azure Machine Learning.According to Manish Prakash, Country General Manager-PS, Health and Education, Microsoft India, said, "With AI being the defining technology of our time, it is transforming lives and industry and the jobs of tomorrow will require a different skillset. This will require more collaborations and training and working with AI. That’s why it has become more critical than ever for educational institutions to integrate new cloud and AI technologies. The program is an attempt to ramp up the institutional set-up and build capabilities among the educators to educate the workforce of tomorrow." The program aims to build up the cognitive skills and in-depth understanding of developing intelligent cloud connected solutions for applications across industry. Earlier in April this year, the company announced Microsoft Professional Program In AI as a learning track open to the public. The program was developed to provide job ready skills to programmers who wanted to hone their skills in AI and data science with a series of online courses which featured hands-on labs and expert instructors as well. This program also included developer-focused AI school that provided a bunch of assets to help build AI skills.
nd the summarized text with 2lines as an input is
Envisioned as a three-year collaborative program, Intelligent Cloud Hub will support around 100 institutions with AI infrastructure, course content and curriculum, developer support, development tools and give students access to cloud and AI services. The company will provide AI development tools and Azure AI services such as Microsoft Cognitive Services, Bot Services and Azure Machine Learning. According to Manish Prakash, Country General Manager-PS, Health and Education, Microsoft India, said, "With AI being the defining technology of our time, it is transforming lives and industry and the jobs of tomorrow will require a different skillset.
As you can see, it does a pretty good job. You can further customize it to reduce to number to character instead of lines.
It is important to understand that we have used text rank as an approach to rank the sentences. TextRank does not rely on any previous training data and can work with any arbitrary piece of text. TextRank is a general purpose graph-based ranking algorithm for NLP.
There are much-advanced techniques available for text summarization. If you are new to it, you can start with an interesting research paper named Text Summarization Techniques: A Brief Survey