A novel approach to text document embedding in high dimensional spaces for information Retrieval in Large Databases

Chiranjeevi, H S and Shenoy, Manjula K and Sunadar, Syam D and Prabhu, Srikanth (2017) A novel approach to text document embedding in high dimensional spaces for information Retrieval in Large Databases. In: International Conference on Computational Intelligence and Computing Research, 14/12/2017, Coimbatore.

[img] PDF
1028.pdf - Published Version
Restricted to Registered users only

Download (279kB) | Request a copy

Abstract

for many applications such as document classification, information retrieval, and machine translation. he representations accuracy of text document information will ave broad applications in healthcare analytics. In the existing ystem, the text document information and query have been represented without conducting the query understanding. In this ork, we propose text document embedding in high dimensional pace using the Meta information, which learns distributed epresentations of health care datasets. Relational networks are sed to represent the domain-specific Meta information to handle earch challenges. The developed relation network use the predefined ext document information processed based on vector pace, term weights calculated using TF-IDF method. The roposed method conduct the information understanding by inding the relationship between the text documents and achieve he search accuracy.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Text documents, Information retrieval, Vector space, Term Frequency-Inverse Document Frequency (TF-IDF), Search system, relational network, Meta information
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 30 Dec 2017 09:16
Last Modified: 30 Dec 2017 09:16
URI: http://eprints.manipal.edu/id/eprint/150383

Actions (login required)

View Item View Item