GRAMMAR RULE BASED INFORMATION RETRIEVAL MODEL FOR BIG DATA

Abstract
Though Information Retrieval (IR) in big data has been an active field of research for past few years; the popularity of the native languages presents a unique challenge in big data information retrieval systems. There is a need to retrieve information which is present in English and display it in the native language for users. This aim of cross language information retrieval is complicated by unique features of the native languages such as: morphology, compound word formations, word spelling variations, ambiguity, word synonym, other language influence and etc. To overcome some of these issues, the native language is modeled using a grammar rule based approach in this work. The advantage of this approach is that the native language is modeled and its unique features are encoded using a set of inference rules. This rule base coupled with the customized ontological system shows considerable potential and is found to show better precision and recall.

Authors
T. Nadana Ravishankar1, Dinesh Mavaluru2, R. Jayabrabu3
B.S. Abdur Rahman University, India1, Saudi Electronic University, Kingdom of Saudi Arabia2, Jazan University, Kingdom of Saudi Arabia3

Keywords
Information Retrieval, Big Data, Cross Language Information Retrieval, Query Disambiguation, Telugu
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 5 , Issue: 4 )
Date of Publication :
July 2015

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.