International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
Text Summarization using NLP B Rajesh1, K Nimai Chaitanya2, P Tejesh Govardhan3, K Krishna Mahesh4, B Sudarshan5 1Assistant Professor, Dept. of CSE GITAM(Deemed to be University), Visakhapatnam, Andhra Pradesh, India 2,3,4,5 Student, GITAM(Deemed to be University), Visakhapatnam, Andhra Pradesh, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - There is a lot of information available on the
internet today, but it can be difficult to obtain it quickly and efficiently. It can be difficult to find exactly the information you need to understand a particular topic. The context of the text is useful for extracting the most important information from the various contents of the text. In the age of information overload on the Internet, automatic document summarization is especially important for retrieving important information from many electronic documents. Text summarization that uses natural language processing to summarize text. There are many ways to describe different methods of explanation: extraction and abstraction from single or mixed data; the purpose of content reduction; features of the manuscript; process from shallow to deep; and the content of the article. With the increase in internet and smartphone usage, online shopping has also increased. Everyone wants their belongings to be delivered to their home in good condition. But reading these long reviews is not easy for everyone. Therefore, brevity should be able to reduce long words into short sentences with shorter words describing the same subject.
Fig-1: Extractive and Abstractive 1.1 Extractive Summarization It involves selecting and rearranging sentences directly from the source text and extracting the most informative sentences to form a coherent summary. The methodology of the extractive text summarization includes reading the document, it will then clean the text and then weighs the sentence scores by the nlargest() function in the Heapq model. The process of Extractive text summarization includes the following: I. Text Pre-Processing II. Sentence Scoring III. Sentence Selection IV. Post-processing
Keywords - Text summarization, information retrieval, electronic text, extraction, abstraction, online shopping.
1.INTRODUCTION In an era characterized by the exponential growth of digital information, the ability to distil large volumes of text into concise yet informative summaries have become an essential task. Natural Language Processing (NLP) revolutionizes how we interact with and make sense of textual data. Text summarization, a prominent application of NLP, addresses the challenge of condensing lengthy documents, articles, or passages into shorter versions while retaining the core ideas and critical information.
1.2 Abstractive Summarization Abstractive summarization goes a step further by generating new sentences that has the same meaning of the original content. This approach requires a deeper understanding of language and context, often involving techniques such as language generation models.
The art of summarization dates back centuries, from early human-curated abstracts to modern- day algorithms driven by computational linguistics. However, the surge in online content creation and the demand for quick access to information has prompted the need for automated and efficient text summarization techniques. NLP techniques have truly shined, enabling machines to comprehend, analyze, and generate human-like summaries.
The challenges in text summarization are multifaceted. NLP models must discern the importance of sentences, grasp contextual nuances, and ensure grammatical accuracy while crafting summaries. Additionally, they must handle various text types, such as news articles, research papers, social media posts, and more. The applications of NLP-based text summarization are diverse and impactful. News agencies can automate the process of generating news digests, enabling readers to grasp the day's events quickly. Researchers can sift through numerous academic papers to find relevant studies efficiently. It is used for summarizing the reviews of
There are two primary approaches to text summarization: extractive and abstractive summarization.
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 702