PROJECT PRESENTATION ON

BLOG POST SUMMARIZATION

SEM-4

GUIDE: Prof. DAKSHATA ARGADE

STUDENTS’ NAMES:- ID:- ROLL NO.:-

Devendra Neelam TU4F2122003 3

Vishav Pathania TU4F2122005 5
Pratham Handa TU4F2122036 35
Sudhakar Jha TU4F2122037 36

DEPARTMENT OF INFORMATION TECHNOLOGY

1
 OUTLINE

1. Abstract
2. Introduction
3. Literature Review
4. Problem Statement
5. Objectives
6. Methodology
7. Conclusion

DEPARTMENT OF INFORMATION TECHNOLOGY

2
 ABSTRACT

• This is a blog post summarization project using the Hugging Face API’s
Google/Pegasus-CNN_dailymail model.

• The project takes an input blog post URL or text and summarizes it into an
accurate summary.

• The language of the blog post can be selected from the options: English, Hindi,
Marathi and other such languages. The summarized text can be played as
speech/audio using Text-to-Speech (TTS) functionality.

• The project provides an interactive user interface for input and output.

DEPARTMENT OF INFORMATION TECHNOLOGY

3
 INTRODUCTION

• The internet is a vast ocean of knowledge that contains various important

information but at the same time it also contains many irrelevant and repetitive
material.

• A blog post summarizer is a tool that uses algorithms to compress such lengthy
blog posts or articles into shorter, concise summaries.

• What we will implement is a type of text summarizer that can make a synopsis of
an article or post while keeping the important information and meaning intact to
it.

DEPARTMENT OF INFORMATION TECHNOLOGY

4
 LITERATURE SURVEY

• Automated summaries began the search for automatic retrieval of data from documents
using our precious time. H.P. Luhn was the first to invent an automatic summary of the
text in 1958.

• We browsed Various studies and research related to text summarization and natural
language processing. The most popular summarization algorithms include TextRank,
LexRank, Latent Semantic Analysis, and Luhn’s Method.

• Additionally, machine learning algorithms, such as supervised and unsupervised

learning, can be used to improve accuracy and performance of the summarizer.

DEPARTMENT OF INFORMATION TECHNOLOGY

5
 LITERATURE SURVEY
Sr Title Citing Technology Advantages Drawbacks
no. /Method
1. Text Virender Dehru et al TextRank, Time-saving, Grammatical
Summarization 2021 IOP Conf. Ser.: extractive scalable errors,
Techniques and Mater. Sci. Eng. 1099 summarization. Not 100%
Applications 012042 Python. accurate
2. Text Summarizer IRE Journals, Vol. 6 NLP, Foreign language Repeated
using NLP issue 1,July 2022 extractive readable, summary if
ISSN: 2456-8880 summarization Short input repeated
input is given
3. Automatic Text Neto, J.L., Freitas, Compression Trainable Language-
Summarization A.A., Kaestner, C.A.A. rate, Algorithm, restricted.
Using a Machine (2002). In: Machine Accessible on all
Learning Bittencourt, G., Learning devices.
Approach. Ramalho, G.L. (eds)
Advances in Artificial
Intelligence. SBIA
2002. Lecture Notes
in Computer
DEPARTMENT OF INFORMATION TECHNOLOGY
Science(), vol 2507 6
Heidelberg.
 PROBLEM STATEMENT

• There is a great need for text summary techniques to address the amount of text data
available online to help people find the right information and use the right information
quickly.

• The text data on the internet has grown exponentially which is still a precious source of
information and knowledge that needs to be efficiently summarized.

• It is needed to have a compact variant of data, while preserving its knowledge and actual
meaning.

DEPARTMENT OF INFORMATION TECHNOLOGY

7
 OBJECTIVE

• To Generate Fast And Decent Summaries.

• To save time and effort by quickly summarizing long blog posts.

• To summarize the news and let user read news with more speed and accuracy.

DEPARTMENT OF INFORMATION TECHNOLOGY

8
BLOCK DIAGRAM / SYSTEM ARCHITECTURE

9
DEPARTMENT OF INFORMATION TECHNOLOGY
 PROPOSED METHODOLOGY

• Collection of blog posts or texts to be summarized. Pre-processing of the

collected text data to clean and prepare it for summarization.

• Passing Extracted Text and Api key to HuggingFace Api and Get Summary of
the text as a Response from Api

• Presentation of the summarized text to the user.

• This project aims to provide a concise version of a given text while retaining
its important information and essence.

• The steps involved in this project will help to achieve this goal efficiently.

DEPARTMENT OF INFORMATION TECHNOLOGY

10
 CONCLUSION

• A summarization tool for blog posts has been developed

• The tool is accessible and user-friendly
• Advanced algorithms and techniques are used to generate high-quality
summaries
• Thorough testing has demonstrated good performance in generating accurate
and concise summaries
• The project has successfully achieved its objectives
• The tool has the potential to significantly impact the way people access and
consume information
• Users can easily get a quick summary of blog posts, saving time and
improving efficiency.

DEPARTMENT OF INFORMATION TECHNOLOGY

11
 REFERENCES

• Richa Sharma, Prachi Sharma, “A Survey of Extractive Text Summarization”, International Journal of Advanced
Research in Computer Science and Software Engineering, Volume 6, 2016.

• Farshad Kyoomarsi, Hamid Khosravi, Esfandiar Eslami and Pooya Khosravyan Dehkordy, “Optimizing Text
Summarization Based on Fuzzy Logic”, In proceedings of Seventh IEEE/ACIS International Conference on
Computer and Information Science, IEEE, University of Shahid Bahonar Kerman, UK, 347-352, 2008.

• Sinha, Aakash, Abhishek Yadav, and Akshay Gahlot. "Extractive text summarization using neural networks." arXiv
preprint arXiv:1802.10137 (2018).

• Peter J. Liu, and Christopher D. Manning. "Get to the point: Summarization with pointer-generator networks."
arXiv preprint arXiv:1704.04368 (2017).

12
 REFERENCES

• Adhika Widyassari, S.R. (2020). Review of Automatic text Summarization techniques & methods. Journal of King
Saud University- Computerand Information Sciences, 18.

• Liu, Linqing, et al. "Generative adversarial network for abstractive text summarization." Proceedings of the AAAI
Conference on Artificial Intelligence. Vol. 32. No. 1. 2018.

• Gupta , V., & Lehal, G.S. (2009). A survey of text mining techniques and applications. Journal of emerging technology
in web intelligence, I(1), 60-76.

• Tas, O., & Kiyani, F. (2007). A survey automatic text summarization. Press Academia Procedia, 5(1), 205-213.

• Allahyari, M., Poriyeh, S., Assefi, M., Safaei, S., Trippe, E.D., Gutierrez, J.B., & Kochut, K.
(2017). Text summarization techniques: a brief survey. arXiv preprint arXiv:1707.02268.

13