You are on page 1of 9

TEXT SUMMARIZER

USING MACHINE
LEARNING
GUIDE: MOHAMMED SHAHIR
Ms. AMRUTHA KARTHIKEYAN 39A
NAME OF THE ORGANIZATION
ALLIEVO LEARNING CENTRE
PALARIVATTOM
KERALA
682025

EXTERNAL GUIDE FRONTEND –HTML,CSS


ROSHAN JOSE BACKEND- PYTHON,MYSQL
PROJECT MANAGER
INTRODUCTION

 Text summarization is the technique for generating a concise and precise


summary of voluminous texts while focusing on the sections that convey
useful information, and without losing the overall meaning.
 Automatic text summarization aims to transform lengthy documents into
shortened versions, something which could be difficult and costly to undertake
if done manually.
EXISTING SYSTEM
 Most of the existing methods for document summarization use the information
present in the given document.
 Comments left by readers on Web documents contain valuable information that
can be utilized in various information retrieval tasks including document
search, visualization and summarization.

PROPOSED SYSTEM
 The input text is processed using natural language processing and processed
input is converted into vector form using word embedding.
 Sentence ranking is done between sentences to extract higher ranked sentence.
 The user can easily input the large text and the system provides the
summarized version of the large text.
MODULES

 LOGIN
Users input their login information, comprising a username and password.
The system processes this input to ascertain its validity. If the entered
information is deemed valid, the user is successfully logged into a new page;
otherwise, an indication of invalid details is displayed.
 REGISTRATION
The system accepts input consisting of usernames, passwords, and other
essential user details. It then processes this information to determine its
validity and checks if the user is already registered. Upon successful validation
and verification, the new user is successfully registered into the system.
 TEXT SUMMARY
The introduction outlines the process of summarizing extensive text data.
Users upload a significant amount of text data as input. This data is then
processed through a model utilizing the BERT algorithm for summarization.
The output yields the summarized text data, providing users with a
condensed version of the original content.
CONCLUSION

 The intention of text summarizer is to create a coherent and fluent


summary having only the main points outlined in the document.
 The generation of summaries can be integrated into these systems
as an intermediate stage which helps to reduce the length of the
document.
REFERENCES

 Ramesh Nallapati, Bowen Zhou, Caglar Gulcehre, Bing Xiang, et


al. Abstractive text summarization using sequence-to-sequence
rnns and beyond. arXiv prepriarXiv:1602.06023, 2016
 Alexander M Rush, Sumit Chopra, and Jason Weston. A neural
attention model for abstractive sentence summarization,2017.
 Approaching Text Summarization using Machine Learning and
Deep Neural Network -https://youtu.be/0l70K5c5NkM
 Summarize Written Text using Google's BERT | Machine
Learning | Deep Learning-https://youtu.be/pTHBZ6AyzOg
THANK YOU!

You might also like