Text Summarizers for Education News Articles
Journal Title: International Journal of Engineering and Science Invention - Year 2018, Vol 7, Issue 4
Abstract
Text summarization is a powerful text mining technique for condensing the contents of the documents without loss of context and information. As the text summarization models are highly adopted in areas like natural language processing, information retrieval, text compression, email thread summarization, library sciences there is necessity for building innovative text summarization models. In this research work, the text summarization models have been built using TextRank algorithm, though algorithm like LexRank, LSA have been used earlier. New dataset has been developed to test the performance of TextRank based text summarization model. The model is compared with LexRank and LSA based text summarization models and opinosis datasets. ROUGE scores such as ROUGE 1, ROUGE 2, ROUGE L which includes precision, recall, Fmeasure along with cosine similarity and relative utility are used as metrics for performance evaluation. The comparative analysis of all three summarizers shows that Text rank algorithm performs better for education dataset than other two algorithms.
Authors and Affiliations
Vishnu Preethi K, Vijaya MS
Keywords
Related Articles
- EP ID EP396578
- DOI -
- Views 94
- Downloads 0
Field and Theoretical Analysis of Accelerated Consolidation Using Vertical Drains
Mumbai is the region consisting of soft compressible marine clay deposits. There are several construction problems on such soils and thus ground improvement is need to be carried out. Vertical drains is generally preferr...
Engine Lock And Tracking System
An Efficient Vehicle Tracking System Is Designed And Implemented For Tracking The Movement Of Any Equipped Vehicle From Any Location At Any Time. The Proposed System Made Good Use Of A Popular Technology That Combines A...
A Novel Architecture for Designing a Multimodal User Interface to Relational Databases
A user interface of a relational database acts like a link between the user and the relational database. It allows the users to retrieve data from the database. As the number of information workers is increasing day-by-d...
Performance Evaluation of Diesel engine by feature selection of Exhaust using Machine Learning Algorithm
In Diesel Engines, it has always been a field of interest, the control of Air-Fuel Ratio (AFR) in its transient operating conditions. Exhaust gas related to emission of CO2, NOx, PM, CO and unburned HC, together with the...
Content Based Image Retrieval Based On Internal Regions Using Clustering Methods in Interactive Genetic Algorithm
Content Based Image Retrieval (CBIR) is a way to extend and improve query methods for searching the image in databases. In CBIR, a description of the required content in terms of visual features of an image is required....