Preferred Language
Articles
/
ijs-4039
Word Embedding Methods for Word Representation in Deep Learning for Natural Language Processing
...Show More Authors

    Natural Language Processing (NLP) deals with analysing, understanding and generating languages likes human. One of the challenges of NLP is training computers to understand the way of learning and using a language as human.  Every training session consists of several types of sentences with different context and linguistic structures. Meaning of a sentence depends on actual meaning of main words with their correct positions. Same word can be used as a noun or adjective or others based on their position. In NLP, Word Embedding is a powerful method which is trained on large collection of texts and encoded general semantic and syntactic information of words. Choosing a right word embedding generates more efficient result than others. Most of the papers used pretrained word embedding vector in deep learning for NLP processing. But, the major issue of pretrained word embedding vector is that it can’t use for all types of NLP processing. In this paper, a local word embedding vector formation process have been proposed and shown a comparison between pretrained and local word embedding vectors for Bengali language. The Keras framework is used in Python for local word embedding implementation and analysis section of this paper shows proposed model produced 87.84% accuracy result which is better than fastText pretrained word embedding vectors accuracy 86.75%. Using this proposed method NLP researchers of Bengali language can easily build the specific word embedding vectors for word representation in Natural Language Processing.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Sun Jun 30 2019
Journal Name
Journal Of Global Pharma Technology
Synthesis, Spectral and Antibacterial Activity of Mixed Ligand from Lanthanium (III) Complexes of Schiff Base Ligand with Some Amino Acids
...Show More Authors

In this work, lanthanium (III) complexes were synthesized using by Schiff base ligand (L) derived from benzaldehyde and o-aminoaniline with five amino acids (AA) from glycine (Gly), L-alanine (Ala), L-valine (Val), L-asparagine (Asp) and DL- phenylalanine (Phe). The Schiff base ligand has been characterized by elemental analysis, (MASS, FTIR, 1HNMR, 13CNMR, UV-VIS) electronic spectra. The structures of the new complexes have been described of analysis of elements, molar conductivity, (UV-Vis electronic, FTIR, mass) spectra also magnetic moment. The molar conductivity values of the complexes indicat this every of complexes are electrolytes and other analytical studies reveal octahedral geometry for La (III) ion. The Schiff base ligand, five

... Show More
View Publication
Publication Date
Sat Dec 24 2022
Journal Name
Wasit Journal For Pure Science
β*-Regular supra topological spaces
...Show More Authors

Form the series of generalization of the topic of supra topology is the generalization of separation axioms . In this paper we have been introduced (S * - SS *) regular spaces . Most of the properties of both spaces have been investigated and reinforced with examples . In the last part we presented the notations of supra *- -space ( =0,1) and we studied their relationship with (S * - SS *) regular spaces.

Publication Date
Fri Jul 01 2022
Journal Name
Iraqi Journal Of Science
Spam Filtering based on Naïve Bayesian with Information Gain and Ant Colony System
...Show More Authors

This research introduces a proposed hybrid Spam Filtering System (SFS) which consists of Ant Colony System (ACS), information gain (IG) and Naïve Bayesian (NB). The aim of the proposed hybrid spam filtering is to classify the e-mails with high accuracy. The hybrid spam filtering consists of three consequence stages. In the first stage, the information gain (IG) for each attributes (i.e. weight for each feature) is computed. Then, the Ant Colony System algorithm selects the best features that the most intrinsic correlated attributes in classification. Finally, the third stage is dedicated to classify the e-mail using Naïve Bayesian (NB) algorithm. The experiment is conducted on spambase dataset. The result shows that the accuracy of NB

... Show More
View Publication Preview PDF
Publication Date
Tue Dec 31 2019
Journal Name
Journal Of Economics And Administrative Sciences
Prevent administrative and financial corruption behaviors by activating the functions of the organizational immunity system
...Show More Authors

The current research aims at testing the relationship between organizational immunity and preventing administrative and financial corruption (AFC) in Iraq. The Statistical Package for the Social Sciences program (R& SPSS) was used to analyse the associated questionnaire data. The research problem has examined how to activate the functions of the organizational immune system to enable it to face organizational risks, attempt to prevent administrative and financial corruption, and access the mechanisms by which to develop organizational immunity. A sample of 161 individuals was taken who worked in the Directorate General of Education, Karbala. Also, it was concluded to a lack of memory function for organizational immunity. In a

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Sun Dec 19 2021
Journal Name
Iraqi Journal Of Science
Strongly Coretractable Modules
...Show More Authors

Let R be a ring with identity and M be a right unitary R-module. In this paper we
introduce the notion of strongly coretractable modules. Some basic properties of this
class of modules are investigated and some relationships between these modules and
other related concepts are introduced. 

View Publication Preview PDF
Publication Date
Mon May 31 2021
Journal Name
Iraqi Journal Of Science
Jordan Left Derivation and Centralizer on Skew Matrix Gamma Ring
...Show More Authors

We define skew matrix gamma ring and describe the constitution of Jordan left centralizers and derivations on skew matrix gamma ring on a  -ring. We also show the properties of these concepts.

View Publication Preview PDF
Scopus Crossref
Publication Date
Thu Sep 13 2018
Journal Name
Baghdad Science Journal
On Soft Turning Points
...Show More Authors

The soft sets were known since 1999, and because of their wide applications and their great flexibility to solve the problems, we used these concepts to define new types of soft limit points, that we called soft turning points.Finally, we used these points to define new types of soft separation axioms and we study their properties.

View Publication Preview PDF
Scopus (16)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Sun Aug 20 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Study of Some physical and chemical properties of sand dune of lower Mesopotamian Plain
...Show More Authors

This investigation was conducted to examine some physical and chemical properties of sand dunes collected from Basrah (1 '2 and 3) 'Nassiriya (4 and 5) and Amara (6) provinces that situated in lower Mesopotamia plain.

 

The results indicate clearly that the dominant particles in the samples were sand that were ranging from (81) % to (97) %, however the aggregated size of (0.1 - 0.25) mm were predominates in the investigated sand dunes of the region . Also the study shows that the content of the organic matter and potassium ions were very low (0.1- 0.4% '0.02 -0.22 meq I 100 gm soil. Further more the current result shows high a percentage of calcium carbonate (20.3 - 42.5%). In addition, the study has found a

... Show More
View Publication Preview PDF
Publication Date
Sun Jun 05 2016
Journal Name
Baghdad Science Journal
Synthesis and Characterization of New Mesomorphic Azo Compounds and Study their Photoluminesecence Properties
...Show More Authors

The preparation of a new Azo compounds of highly conjugated dimeric and polymeric liquid crystal to achieve the crystalline characteristics Which have structures assigned based on elemental analysis, IR 1HNMR and CHNS-O while mesogenic properties have been set for DSC and hot-stage polarizing optical microscopy. The compounds show enantiotropicnematic phase being displayed. The compounds show photoluminescence properties in the organic solution at room temperature, with the fluorescence band centered around 400 nm.

View Publication Preview PDF
Crossref
Publication Date
Wed Apr 02 2014
Journal Name
Journal Of Theoretical And Applied Information Technology
TUMOR BRAIN DETECTION THROUGH MR IMAGES: A REVIEW OF LITERATURE
...Show More Authors

Today’s modern medical imaging research faces the challenge of detecting brain tumor through Magnetic Resonance Images (MRI). Normally, to produce images of soft tissue of human body, MRI images are used by experts. It is used for analysis of human organs to replace surgery. For brain tumor detection, image segmentation is required. For this purpose, the brain is partitioned into two distinct regions. This is considered to be one of the most important but difficult part of the process of detecting brain tumor. Hence, it is highly necessary that segmentation of the MRI images must be done accurately before asking the computer to do the exact diagnosis. Earlier, a variety of algorithms were developed for segmentation of MRI images by usin

... Show More
Scopus (45)
Scopus