Department of Computer Science and Engineering

PROJECT NAME

INCREMENTAL INFORMATION EXTRACTION USING RDBMS

Project Coordinator : Dr T.V AnanthanGuide Name : Golda selia

Batch : CSE C20Group members:NISHIKANT (REG NO-91061101068 CSE-B IV yr)SURAJ KUMAR (REG NO-91061101113 CSE-C IV yr)UPENDRA KUMAR (REG NO-91061101114 CSE-C IV yr)

DR. M.G.R EDUCATIONAL & RESEARCH INSTITUTE UNIVERSITY

CONTENT:-INTRODUCTION

METHODOLOGY

ARCHITECTURE

DETAILS OF THE MODULE

RESULT COMPARISON

PROJECT TITLE

INCREMENTAL INFORMATION EXTRACTION

USING RDBMS

Data mining is an important part of knowledge discovery process that analyzes large enormous set of data and gives us unknown, hidden and useful information and knowledge.

A major objective of this project is to provide automated query generation components so that casual users do not have to learn the query language in order to perform extraction.

In medical applications it will develop a tool that can help casual users to make timely and accurate decisions.

INTRODUCTION

METHODOLOGYIn this project we describe a novel approach

for information extraction in which extraction needs are expressed in the form of DATABASE QUERIES, which are evaluated and optimized by database systems.

Using database queries for information extraction enables generic extraction and minimizes reprocessing of data by performing incremental extraction to identify which part of the data is affected by the change of components or goals.

The proposed information extraction is composed of two phases:Initial Phase: The generated syntactic parse trees and

semantic entity tagging of the processed text is stored in a relational database, called parse tree database (PTDB).

Extraction Phase Extraction is then achieved by issuing

database queries to PTDB. To express extraction patterns, we designed and implemented a query language called parse tree query language (PTQL) that is suitable for generic extraction.

ARCHITECTURAL DIAGRAM

DETAILS OF THE MODULE

Database module : In database module we are entering the database name Medline and view tables from that database and select one table as drug from list of tables which we want to proceed for our project. Then the table is added to information retrieval engine (IR), and then select process button. Then the information in that selected table is being processed

MODULE 1: DATABASE MODULE

Entity extraction module:

In this module which contains some process, there is SEARCH and CLEAR, It shows a pipeline of text processing modules in order to perform relationship extraction. These include.

Sentence splitting: Identifies sentences from a paragraph of text,

Tokenization: Identifies word tokens from sentences,

Named entity recognition: Identifies mentions of entity types of interest.

MODULE 2

2.ENTITY EXTRACTION MODULE

Parser module:

In this module will identify grammatical structures of sentences, and Obtains relationships based on a set of extraction.

The extraction patterns over parse trees can be expressed in this proposed parse tree query language.

 

3. PARSER MODULE

Query evaluation module:

In this module, the PTQL query evaluator takes a PTQL query and transforms it into keyword-based queries and SQL queries, which are evaluated by the underlying RDBMS and information retrieval (IR) engine.

It provides automated query generation components so that casual users do not have to learn the query language in order to perform extraction.

Query evaluation module:

RESULT COMPARISON

Our experiments show that in the event of deployment of a new module, our incremental extraction approach reduces the processing time by 89.64 percent as compared to a traditional pipeline approach. By applying our methods to a corpus of 17 million biomedical abstracts,

our experiments show that the query performance is efficient for real-time applications. Our experiments also revealed that our approach achieves high quality extraction results.

THANK YOU