Text Summarization Approaches for NLP – Practical Guide with Generative Examples

Text summarization in NLP is the process of summarizing the information in large texts for quicker consumption. In this article, I will walk you through the traditional extractive as well as the advanced generative methods to implement Text Summarization in Python.

Contents

  1. Introduction
  2. Types of Text Summarization
  3. Text Summarization using Gensim
  4. Text Summarization with sumy
  5. What is Abstractive Text Summarization
  6. T5 Transformers for Text Summarization
  7. BART Transformers for Text Summarization
  8. GPT-2 Transformers for Text Summarization
  9. XLM Transformers for Text Summarization

Introduction

When you open news sites, do you just start reading every news article? Probably not. We typically glance the short news summary and then read more details if interested. Short, informative summaries of the news is now everywhere like magazines, news aggregator apps, research sites, etc.

Well, It is possible to create the summaries automatically as the news comes in from various sources around the world.

The method of extracting these summaries from the original huge text without losing vital information is called as Text Summarization. It is essential for the summary to be a fluent, continuous and depict the significant.

In fact, the google news, the inshorts app and various other news aggregator apps take advantage of text summarization algorithms.

In this post, I discuss and use various traditional and advanced methods to implement automatic Text Summarization.

Image showing the Text Summarization

Types of Text Summarization

Text summarization methods can be grouped into two main categories: Extractive and Abstractive methods

  • Extractive Text Summarization

    It is the traditional method developed first. The main objective is to identify the significant sentences of the text and add them to the summary. You need to note that the summary obtained contains exact sentences from the original text.

  • Abstractive Text Summarization

    It is a more advanced method, many advancements keep coming out frequently(I will cover some of the best here). The approach is to identify the important sections, interpret the context and reproduce in a new way. This ensures that the core information is conveyed through shortest text possible. Note that here, the sentences in summary are generated, not just extracted from original text.

In the next sections, I will discuss different extractive and abstractive methods. At the end, you can compare the results and know for yourself the advantages and limitations of each method.

Text Summarization using Gensim with TextRank

gensim is a very handy python library for performing NLP tasks. The text summarization process using gensim library is based on TextRank Algorithm

What is TextRank algorithm?

TextRank is an extractive summarization technique. It is based on the concept that words which occur more frequently are significant. Hence , the sentences containing highly frequent words are important .

Based on this , the algorithm assigns scores to each sentence in the text . The top-ranked sentences make it to the summary.

Consider the below article on junk foods which has to be summarized.

original_text = 'Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

After importing the gensim package, the first step is to import summarize from gensim.summarization. It is an in-built function that implements TextRank.

# Importing package and summarizer
import gensim
from gensim.summarization import summarize

Next, pass the text corpus as input to summarize function

# Passing the text corpus to summarizer 
short_summary = summarize(original_text)
print(short_summary)
They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers.
Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life.
Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body.
It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes.
Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers.
It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol.
High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning.
One who like junk food develop more risk to put on extra weight and become fatter and unhealthier.
Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert.
For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats.

Seems too long right!

Yes, but you can control how long your summarized text should be.

You can change the default parameters of the summarize function according to your requirements.

The parameters are:

  1. ratio: It can take values between 0 to 1. It represents the proportion of the summary compared to the original text.

  2. word_count: It decides the no of words in the summary.

Let me show you how to use the parameters in above example.

# Summarization by ratio
summary_by_ratio=summarize(original_text,ratio=0.1)
print(summary_by_ratio)
They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers.
Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life.
Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers.
It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol.
High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning.

In the above output, you can notice that only 10% of original text is taken as summary.

Likewise, you can summarize using word_count.

# Summarization by word count
summary_by_word_count=summarize(article_text,word_count=30)
print(summary_by_word_count)
They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers.

What if you provide contradicting word_count and ratio value ?

In case both are mentioned, then the summarize function ignores the ratio. So, only the word_count parameter is taken.

# Summarization when both ratio & word count is given
summary=summarize(article_text, ratio=0.1, word_count=30)
print(summary)
They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers.

It is clear that word_count has been followed.

Similar to TextRank , there are various other algorithms which perform summarization. Let’s look at it one by one.

Text Summarization with Sumy

Along with TextRank , there are various other algorithms to summarize text.

Don’t you think it would be very smooth and beneficial to have a library, which will let you perform summarization through multiple algorithms?

Fortunately, we already have the sumy library for it !

sumy libraray provides you several algorithms to implement Text Summarzation. Just import your desired algorithm rather having to code it on your own.

In this section, I shall discuss on implementation of the below algorithms for summarization using sumy :

  1. LexRank
  2. Luhn
  3. Latent Semantic Analysis, LSA
  4. KL-Sum

First , import the library through below command

# Installing and Importing sumy
!pip install sumy
import sumy

You can acesss different summarizers available through sumy.summarizers module.

sumy.summarizers
<module 'sumy.summarizers' from '/usr/local/lib/python3.6/dist-packages/sumy/summarizers/__init__.py'>

LexRank

First, let me introduce you to summarization with LexRank.

How does LexRank work?

A sentence which is similar to many other sentences of the text has a high probability of being important. The approach of LexRank is that a particular sentence is recommended by other similar sentences and hence is ranked higher.

Higher the rank, higher is the priority of being included in the summarized text.

I will demonstrate step-by-step on how to summarize the below text

original_text='Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

Next, import PlaintextParser. Here, we have a article stored as a string hence we use it. In case of using website sources etc, there are other parsers available. Along with parser, you have to import Tokenizer for segmenting the raw text into tokens.

# Importing the parser and tokenizer
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer

You can access the summarizers available through sumy.summarizers. Here, I have imported the LexRankSummarizer

# Import the LexRank summarizer
from sumy.summarizers.lex_rank import LexRankSummarizer

As the text source here is a string, you need to use PlainTextParser.from_string() function to initialize the parser. You can specify the language used as input to the Tokenizer.

syntax : PlaintextParser.from_string(cls, string, tokenizer)

# Initializing the parser
my_parser = PlaintextParser.from_string(original_text,Tokenizer('english'))

Next create a summarizer model lex_rank_summarizer to fit your text. The syntax is: lex_rank_summarizer(document, sentences_count).

You can decide the number of sentences you want in the summary through parameter sentences_count.

# Creating a summary of 3 sentences.
lex_rank_summarizer = LexRankSummarizer()
lexrank_summary = lex_rank_summarizer(my_parser.document,sentences_count=3)

# Printing the summary
for sentence in lexrank_summary:
  print(sentence)
It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes.
It is more of fats and cholesterol which will have a harmful impact on your health.
Children will find one way or the other to have it.

Similar to LexRank , there are more text summarizers supported by sumy. In the next section, Let’s do LSA.

LSA (Latent semantic analysis)

Latent Semantic Analysis is a unsupervised learning algorithm that can be used for extractive text summarization.

It extracts semantically significant sentences by applying singular value decomposition(SVD) to the matrix of term-document frequency. To learn more about this algorithm, check out here

Let me demonstrate how to use LSA for summarization . First, import the summarizer from sumy.

# Import the summarizer
from sumy.summarizers.lsa import LsaSummarizer

# Text to summarize
original_text = 'Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

Import the parser and tokenizer for tokenizing the document.

# Parsing the text string using PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.parsers.plaintext import PlaintextParser
parser=PlaintextParser.from_string(original_text,Tokenizer('english'))

The parser has been created . It’s time to initialize the summarizer model and pass your document and desired no of sentences as input.

# creating the summarizer
lsa_summarizer=LsaSummarizer()
lsa_summary= lsa_summarizer(parser.document,3)

# Printing the summary
for sentence in lsa_summary:
    print(sentence)
Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children.
To make things worse, junk food also clogs your arteries and increases the risk of a heart attack.
Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now.

Luhn

Luhn Summarization algorithm’s approach is based on TF-IDF (Term Frequency-Inverse Document Frequency). It is useful when very low frequent words as well as highly frequent words(stopwords) are both not significant.

Based on this, sentence scoring is carried out and the high ranking sentences make it to the summary.

Import the summarizer and the text to summarize .

# Import the summarizer
from sumy.summarizers.luhn import LuhnSummarizer

# text to summarize
original_text='Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

Just like previous methods, initialize the parser through below code.

# Creating the parser
from sumy.nlp.tokenizers import Tokenizer
from sumy.parsers.plaintext import PlaintextParser
parser=PlaintextParser.from_string(original_text,Tokenizer('english'))

Next, instantiate the summarizer with your text doxument. You can decide the no of sentences in your summary through sentences_count parameter.

#  Creating the summarizer
luhn_summarizer=LuhnSummarizer()
luhn_summary=luhn_summarizer(parser.document,sentences_count=3)

# Printing the summary
for sentence in luhn_summary:
  print(sentence)
They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers.
It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes.
Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers.

That makes sense.

KL-Sum

Another extractive method is the KL-Sum algorithm.

It selects sentences based on similarity of word distribution as the original text. It aims to lower the KL-divergence criteria (learn more). It uses greedy optimization approach and keeps adding sentences till the KL-divergence decreases.

Let me show you the performance of it here. First import it from sumy

from sumy.summarizers.kl import KLSummarizer

Next , create the parser to read from the original text

# Our text to perform summarization
original_text='Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

# Creating the parser
from sumy.nlp.tokenizers import Tokenizer
from sumy.parsers.plaintext import PlaintextParser
parser=PlaintextParser.from_string(original_text,Tokenizer('english'))

Instantiate the summarize and pass the text through parser.document attribute.

# Instantiating the  KLSummarizer
kl_summarizer=KLSummarizer()
kl_summary=kl_summarizer(parser.document,sentences_count=3)

# Printing the summary
for sentence in kl_summary:
    print(sentence)
It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes.
High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning.
Junk food is the easiest way to gain unhealthy weight.

What is Abstractive Text Summarization?

Abstractive summarization is the new state of art method, which generates new sentences that could best represent the whole text. This is better than extractive methods where sentences are just selected from original text for the summary.

How to easily implement abstractive summarization?

A simple and effective way is through the Huggingface’s transformers library.

!pip install transformers
Installing collected packages: sacremoses, sentencepiece, tokenizers, transformers
Successfully installed sacremoses-0.0.43 sentencepiece-0.1.91 tokenizers-0.7.0 transformers-2.11.0

HuggingFace supports state of the art models to implement tasks such as summarization, classification, etc.. Some common models are GPT-2, GPT-3, BERT , OpenAI, GPT, T5.

Another awesome feature with transformers is that it provides PreTrained models with weights that can be easily instantiated through from_pretrained() method.

You can check the list of currently available PreTrained models here

This section will show you text summarization through different models of transformers library

Summarization with T5 Transformers

T5 is an encoder-decoder model. It converts all language problems into a text-to-text format.

First, you need to import the tokenizer and corresponding model through below command.

It is preferred to use T5ForConditionalGeneration model when the input and output are both sequences.

# Importing requirements
from transformers import T5Tokenizer, T5Config, T5ForConditionalGeneration

# text to summarize
original_text='Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

You can instantiate the pretrained “t5-small” model through .from_pretrained` method. The syntax is mentioned below.

T5ForConditionalGeneration.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)

# Instantiating the model and tokenizer 
my_model = T5ForConditionalGeneration.from_pretrained('t5-small')
tokenizer = T5Tokenizer.from_pretrained('t5-small')
HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1197.0, style=ProgressStyle(description…






HBox(children=(FloatProgress(value=0.0, description='Downloading', max=242136741.0, style=ProgressStyle(descri…






HBox(children=(FloatProgress(value=0.0, description='Downloading', max=791656.0, style=ProgressStyle(descripti…

Next is the most important step which you should not forget. You have to add the string ” summarize: ” at the beginning of your raw text . T5 transformers performs different tasks by prepending the particular prefix to the input text.

# Concatenating the word "summarize:" to raw text
text = "summarize:" + original_text
text
'summarize:Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

If you recall , T5 is a encoder-decoder mode and hence the input sequence should be in the form of a sequence of ids, or input-ids.

How to convert the input text into input-ids ?

This process is called encoding the text and can be achieved through encode() method

# encoding the input text
input_ids=tokenizer.encode(text, return_tensors='pt', max_length=512)

Next, you can pass the input_ids to the function generate(), which will return a sequence of ids corresponding to the summary.

The syntax will be: transformers.PreTrainedModel.generate (input_ids=None, max_length=None, min_length=None, num_beams=None)

Except input_ids, others parameters are optional and can be used to set the summary requirements.

# Generating summary ids
summary_ids = my_model.generate(input_ids)
summary_ids
tensor([[    0, 11797,  4371,    33,     8,  1391,    13,  6900, 11537,   257,
            11,   119,  6716,   114,  8363,     6,   842, 29939,     6,   842]])

You can see that model has returned a tensor with sequence of ids. Now, use the decode() function to generate the summary text from these ids.

It simply performs the inverse of encode() function.

# Decoding the tensor and printing the summary.
t5_summary = tokenizer.decode(summary_ids[0])
print(t5_summary)
junk foods are the source of constipation and other diseases like diabetes, heart ailments, heart

You can observe the summary and spot newly framed sentences unlike the extractive methods. Unlike extractive methods, the above summarized output is not part of the original text.

Summarization with BART Transformers

transformers library of HuggingFace supports summarization with BART models.

Import the model and tokenizer. For problems where there is need to generate sequences , it is preferred to use BartForConditionalGeneration model.

# Importing the model
from transformers import BartForConditionalGeneration, BartTokenizer, BartConfig

” bart-large-cnn” is a pretrained model, fine tuned especially for summarization task. You can load the model using from_pretrained() method as shown below.

# Loading the model and tokenizer for bart-large-cnn

tokenizer=BartTokenizer.from_pretrained('facebook/bart-large-cnn')
model=BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
HBox(children=(FloatProgress(value=0.0, description='Downloading', max=898823.0, style=ProgressStyle(descripti…






HBox(children=(FloatProgress(value=0.0, description='Downloading', max=456318.0, style=ProgressStyle(descripti…






HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1300.0, style=ProgressStyle(description…






HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1625270765.0, style=ProgressStyle(descr…

Let’s say you need to summarize the below text.

original_text = 'Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not a healthy weight. It is more of fats and cholesterol which will have a harmful impact on your health. Junk food is also one of the main reasons for the increase in obesity nowadays.This food only looks and tastes good, other than that, it has no positive points. The amount of calorie your body requires to stay fit is not fulfilled by this food. For instance, foods like French fries, burgers, candy, and cookies, all have high amounts of sugar and fats. Therefore, this can result in long-term illnesses like diabetes and high blood pressure. This may also result in kidney failure. Above all, you can get various nutritional deficiencies when you don’t consume the essential nutrients, vitamins, minerals and more. You become prone to cardiovascular diseases due to the consumption of bad cholesterol and fat plus sodium. In other words, all this interferes with the functioning of your heart. Furthermore, junk food contains a higher level of carbohydrates. It will instantly spike your blood sugar levels. This will result in lethargy, inactiveness, and sleepiness. A person reflex becomes dull overtime and they lead an inactive life. To make things worse, junk food also clogs your arteries and increases the risk of a heart attack. Therefore, it must be avoided at the first instance to save your life from becoming ruined.The main problem with junk food is that people don’t realize its ill effects now. When the time comes, it is too late. Most importantly, the issue is that it does not impact you instantly. It works on your overtime; you will face the consequences sooner or later. Thus, it is better to stop now.You can avoid junk food by encouraging your children from an early age to eat green vegetables. Their taste buds must be developed as such that they find healthy food tasty. Moreover, try to mix things up. Do not serve the same green vegetable daily in the same style. Incorporate different types of healthy food in their diet following different recipes. This will help them to try foods at home rather than being attracted to junk food.In short, do not deprive them completely of it as that will not help. Children will find one way or the other to have it. Make sure you give them junk food in limited quantities and at healthy periods of time. '

You need to pass the input text in the form of a sequence of ids.

For this, use the batch_encode_plus() function with the tokenizer. This function returns a dictionary containing the encoded sequence or sequence pair and other additional information.

Now, How to limit the maximum length of the returned sequence?

Set the max_length parameter in batch_encode_plus().

Next, pass the input_ids to model.generate() function to generate the ids of the summarized output.

# Encoding the inputs and passing them to model.generate()
inputs = tokenizer.batch_encode_plus([original_text],return_tensors='pt')
summary_ids = model.generate(inputs['input_ids'], early_stopping=True)

model.generate() has returned a sequence of ids corresponding to the summary of original text. You can convert the sequence of ids to text through decode() method.

# Decoding and printing the summary
bart_summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(bart_summary)
Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways.

You can see the summary obtained with BART Transformer

Summarization with GPT-2 Transformers

GPT-2 transformer is another major player in text summarization, introduced by OpenAI. Thanks to transformers, the process followed is same just like with BART Transformers.

First, you have to import the tokenizer and model. Make sure that you import a LM Head type model, as it is necessary to generate sequences. Next, load the pretrained gpt-2 model and tokenizer .

After loading the model, you have to encode the input text and pass it as an input to model.generate().

# Importing model and tokenizer
from transformers import GPT2Tokenizer,GPT2LMHeadModel

# Instantiating the model and tokenizer with gpt-2
tokenizer=GPT2Tokenizer.from_pretrained('gpt2')
model=GPT2LMHeadModel.from_pretrained('gpt2')

# Encoding text to get input ids & pass them to model.generate()
inputs=tokenizer.batch_encode_plus([original_text],return_tensors='pt',max_length=512)
summary_ids=model.generate(inputs['input_ids'],early_stopping=True)

The summary_ids contains the sequence of ids corresponding to the text summary . You can decode it and print the summary

# Decoding and printing summary

GPT_summary=tokenizer.decode(summary_ids[0],skip_special_tokens=True)
print(GPT_summary)
Junk foods taste good that’s why it is mostly liked by everyone of any age group especially kids and school going children. They generally ask for the junk food daily because they have been trend so by their parents from the childhood. They never have been discussed by their parents about the harmful effects of junk foods over health. According to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. They are generally fried food found in the market in the packets. They become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. Processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. It makes able a person to gain excessive weight which is called as obesity. Junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. Some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. It is found according to the Centres for Disease Control and Prevention that Kids and children eating junk food are more prone to the type-2 diabetes. In type-2 diabetes our body become unable to regulate blood sugar level. Risk of getting this disease is increasing as one become more obese or overweight. It increases the risk of kidney failure. Eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. It increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. High sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. One who like junk food develop more risk to put on extra weight and become fatter and unhealthier. Junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. Reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. Junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. Junk food is the easiest way to gain unhealthy weight. The amount of fats and sugar in the food makes you gain weight rapidly. However, this is not

Summarization with XLM Transformers

Another transformer type that could be used for summarization are XLM Transformers.

You can import the XLMWithLMHeadModel as it supports generation of sequences.You can load the pretrained xlm-mlm-en-2048 model and tokenizer with weights using from_pretrained() method.

The nexts steps are same as the last three cases. The encoded input text is passed to generate() function with returns id sequence for the summary. You can decode and print the summary.

The below code demonstrates it step-by-step.

# Importing model and tokenizer
from transformers import XLMWithLMHeadModel, XLMTokenizer

# Instantiating the model and tokenizer 
tokenizer=XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
model=XLMWithLMHeadModel.from_pretrained('xlm-mlm-en-2048')

# Encoding text to get input ids & pass them to model.generate()
inputs=tokenizer.batch_encode_plus([original_text],return_tensors='pt',max_length=512)
summary_ids=model.generate(inputs['input_ids'],early_stopping=True)

# Decode and print the summary
XLM_summary=tokenizer.decode(summary_ids[0],skip_special_tokens=True)
print(XLM_summary)

HBox(children=(FloatProgress(value=0.0, description='Downloading', max=2668507970.0, style=ProgressStyle(descr…



junk foods taste good that's why it is mostly liked by everyone of any age group especially kids and school going children. they generally ask for the junk food daily because they have been trend so by their parents from the childhood. they never have been discussed by their parents about the harmful effects of junk foods over health. according to the research by scientists, it has been found that junk foods have negative effects on the health in many ways. they are generally fried food found in the market in the packets. they become high in calories, high in cholesterol, low in healthy nutrients, high in sodium mineral, high in sugar, starch, unhealthy fat, lack of protein and lack of dietary fibers. processed and junk foods are the means of rapid and unhealthy weight gain and negatively impact the whole body throughout the life. it makes able a person to gain excessive weight which is called as obesity. junk foods tastes good and looks good however do not fulfil the healthy calorie requirement of the body. some of the foods like french fries, fried foods, pizza, burgers, candy, soft drinks, baked goods, ice cream, cookies, etc are the example of high-sugar and high-fat containing foods. it is found according to the centres for disease control and prevention that kids and children eating junk food are more prone to the type-2 diabetes. in type-2 diabetes our body become unable to regulate blood sugar level. risk of getting this disease is increasing as one become more obese or overweight. it increases the risk of kidney failure. eating junk food daily lead us to the nutritional deficiencies in the body because it is lack of essential nutrients, vitamins, iron, minerals and dietary fibers. it increases risk of cardiovascular diseases because it is rich in saturated fat, sodium and bad cholesterol. high sodium and bad cholesterol diet increases blood pressure and overloads the heart functioning. one who like junk food develop more risk to put on extra weight and become fatter and unhealthier. junk foods contain high level carbohydrate which spike blood sugar level and make person more lethargic, sleepy and less active and alert. reflexes and senses of the people eating this food become dull day by day thus they live more sedentary life. junk foods are the source of constipation and other disease like diabetes, heart ailments, clogged arteries, heart attack, strokes, etc because of being poor in nutrition. junk food is the easi

You can notice that the XLM_summary isn’t very good. It is because , even though it supports summaization , the model was not finetuned for this task.

We have implemented summarization with various methods ranging from TextRank to transformers. You can analyse the summary we got at the end of every method and choose the best one.

Overall, abstractive summarization using HuggingFace transformers is the current state of the art method. More developments are on the way ! Stay tuned.