Information Retrieval and Natural Language Processing by Sheetal S. Sonawane & Parikshit N. Mahalle & Archana S. Ghotkar

Author:Sheetal S. Sonawane & Parikshit N. Mahalle & Archana S. Ghotkar
Language: eng
Format: epub
ISBN: 9789811699955
Publisher: Springer Singapore

Sheetal S. Sonawane1 , Parikshit N. Mahalle2 and Archana S. Ghotkar3

(1)Department of Computer Engineering, SCTR’s Pune Institute of Computer Technology, Pune, India

(2)Department of Artificial Intelligence and Data Science, Bansilal Ramnath Agarwal Charitable Trust’s, Vishwakarma Institute of Information Technology, Pune, India

(3)Department of Computer Engineering, SCTR’s Pune Institute of Computer Technology, Pune, India

5.1 Introduction

Text has rapidly become the preferred means of information storage and knowledge transfer. As per 2021 update available on Internet World Stats,1 number of people using Internet in the Asia region is 56.2%, in Europe 10.3%, Africa 17.3% and America 8.4%. Nearly half the percentage of world population Internet users is in Asia. 2.7 millions of blog posts are published every day.

The task of automatic understanding and analysis of text became very harder due to unstructured nature of text. Natural language processing and text mining have merged to get information processing and generating information from text. In this big data era, tremendous amount of data is available today so text being no exception to its ever-growing scale. Moreover, many real-world applications combine oral and written communications, and it motivates the need for better text processing. Today machines have become smarter, for example spam filters discard automatically billions of web pages every day. It motivates to develop alternate text representation which works better in the field of information retrieval and natural language processing. This graph is a mathematical structure which is suitable for representing association between entities [1]. This association can be represented by using various parameters. For example, to reach from source to destination, there are multiple routes. These routes can be represented by different parameters like traffic, road condition, availability of toll, etc. Because of strong graph properties, it is very useful in various computer science application. In information retrieval and natural language processing, graph has become very successful in different application. Representing a document using graph is a major step in the process. The graph operations or properties depend on the constructed graph.

This step requires following important sets:1.

The entity of a document representing as node/vertex denoted by V

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.