The errors in the german-to-arabic text AtS with APES and ARS
Reda hussin abo elez , Mohamed fared zaphlol , Mohamed abo kresha , Ahmad el mahdy , Eng. Dahey gaber anem
Professional in computer and system engineering
Professional in computer and system engineering
Ass. Prof . In faculty of science
Ass prof Professional in computer and system engineering
Eng. In computer and system engineering
ABSTRACT
The classification of errors in arabic text
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
2
17
COVID-19 Classification Using Hybrid Deep Learning and
Standard Feature Extraction Techniques
Hassan Ahmed Hassan Elshenbary , Ebeid Ali Ebeid
Department of Mathematics, Faculty of Science, Al-Azhar University, Nasr city, 11884, Cairo, Egypt.
Department of Mathematics, Faculty of Science, Al-Azhar University, Nasr city, 11884, Cairo, Egypt.
ABSTRACT
There is no doubt that COVID-19 disease rapidly spread all over the world, and effected
the daily lives of all of the people. Nowadays, the reverse transcription polymerase
chain reaction is the most way used to detect COVID-19 infection. Due to
time consumed in this method and material limitation in the hospitals, there is a need
to create a robust decision support system based on artificial intelligence to recognize
the infection at an early stage from a medical images. The main contribution in this
research is to develop a robust hybrid feature extraction method for recognizing the
COVID-19 infection. Firstly, we train the alexnet on the images database and extract
the first feature matrix. Then we used DWT and PCA to extract the second feature
matrix from the same images. After that, the desired feature matrices were merged.
Finally, SVM was used to classify the images. Training, validating, and testing of the
proposed method were performed. Experimental results gave (95%, 98.5%) correct
recognition rate on both chest X-Ray and CT images databases. The proposed hybrid
method outperform a lot of standard methods and deep learning neural networks like
alexnet, googlenet.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
3
17
Comparative study Using Simulated Annealing Optimization Technique For Student Performance Prediction
Esraa A. Mahareek , Abeer S. Desuky , Habiba Abdullah El-Zhni
Teaching assistant in faculty of science department of mathematics, Al-Azhar University, Egypt
Professor associate in faculty of science department of mathematics, Al-Azhar University, Egypt
Emeritus professor in faculty of science department of mathematics, Al-Azhar University, Egypt
ABSTRACT
High education is an important and critical part of education all over the world. In recent months, the outbreak of the Covid-19 pandemic has turned the world increasingly to online education; therefore, the need for improving this education system became an urgent matter. Online learning systems are a primal environment for acquiring educational data which can be from different sources, especially academic institutions. These data can be mainly used to analyze and extract utilizable information to help in understanding university students’ performance and identifying factors that affect it. To extract some meaningful information from these large volumes of data, academic organizations must mine the data with high accuracy. Optimization is the process of achieving the best solution for a problem, in this work, three different real datasets were selected, pre-processed, cleaned, and filtered for applying Support Vector Machine (SVM) with Multilayer perceptron kernel (MLP kernel) and optimize its parameters using Simulated Annealing (SA) algorithm to improve the objective function value. While exploring solution space, SA offers the possibility of accepting worse neighbor solutions in a controlled manner to escape from local minima. The results show that the designed system can determine the best SVM parameters using SA and therefore presents better model evaluation.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
4
17
Jellyfish optimization for instance reduction of imbalanced data
Asmaa Hekal Omar , Yomna M. Elbarawy , Abeer S. Desuky
lecturer in faculty of science, Al-Azhar University
lecturer in faculty of science, Al-Azhar University
Assoc. professor in faculty of science, Al-Azhar University
ABSTRACT
The classification of imbalanced datasets has pulled in significant research interest over the previous many years. Imbalanced datasets are common in different fields , for example health, finance, security and others. A wide range of solutions for handle imbalanced datasets center mainly on the class distribution problem and providing more balanced datasets by methods of resampling. The essential rule of these methods is rebalancing an unbalanced dataset using a certain procedure. In this paper we introduce proposed method which includes two stages: first, it rebalances an imbalanced dataset by a particular oversampling algorithm using One-point crossover to generate the new data of minority classes, second, it finds an (sub)optimal subset from the balanced dataset by Jellyfish Search which is the novel optimization method. Experimental results on 18 real imbalanced datasets,
Comparing results with famous oversampling methods and ACOR(Ant Colony Optimization-Resampling) in terms of different appraisal measurements, for example, AUC and G-mean. The proposed method achieves the higher accuracy for 12 datasets, while ACOR, SMOTE and BSO was higher in 3, 3, 1 dataset respectively. The G-mean metric has the higher values with the proposed method in 14 datasets and the AUC in 8 datasets.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
5
17
comparative study using simulated annealing optimization technique for student performance prediction
Abeer S. Desuky , Esraa A. Mahareek , Habiba Abdullah El-Zhni
Professor associate in faculty of science department of mathematics, Al-Azhar University, Egypt
Teaching assistant in faculty of science department of mathematics, Al-Azhar University, Egypt
Professor in faculty of science department of mathematics, Al-Azhar University, Egypt
ABSTRACT
High education is an important and critical part of education all over the world. In recent months, the outbreak of the Covid-19 pandemic has turned the world increasingly to online education; therefore, the need for improving this education system became an urgent matter. Online learning systems are a primal environment for acquiring educational data which can be from different sources, especially academic institutions. These data can be mainly used to analyze and extract utilizable information to help in understanding university students’ performance and identifying factors that affect it. To extract some meaningful information from these large volumes of data, academic organizations must mine the data with high accuracy. Optimization is the process of achieving the best solution for a problem, in this work, three different real datasets were selected, pre-processed, cleaned, and filtered for applying Support Vector Machine (SVM) with Multilayer perceptron kernel (MLP kernel) and optimize its parameters using Simulated Annealing (SA) algorithm to improve the objective function value. While exploring solution space, SA offers the possibility of accepting worse neighbor solutions in a controlled manner to escape from local minima. The results show that the designed system can determine the best SVM parameters using SA and therefore presents better model evaluation.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
6
17
Semantic based pandemic prediction using big data
A.AbuBakr , H. Mancy , Eman K. Elsayed , Kamal A. Eldahshan
Dept. of Mathematics, Computer science Division, Faculty of Science (Girls), Al-Azhar University, Cairo, Egypt
Dept. of Mathematics, Computer science Division, Faculty of Science (Girls), Al-Azhar University, Cairo, Egypt
Dept. of Mathematics, Computer science Division, Faculty of Science (Girls), Al-Azhar University, Cairo, Egypt
Dept. of Mathematics, Computer science Division, Faculty of Science, Al-Azhar University, Cairo, Egypt
ABSTRACT
Nowadays, the world suffers a Coronavirus mutation in 2019 (COVID-19). The COVID-19 data sources possess three main characteristics: big volume, velocity, and variety. Instead of using a statistical hypothesis, the authors proposed Big Data technology, data mining techniques, and Ontology-based approaches to overcome these challenges. This paper introduces big data concepts, technologies, and challenges. It studies NoSQL databases, their types, and the relationship between NoSQL Database and Ontology. A comparative study for pandemic prediction approaches has been reviewed. This review provides important references for building semantic NoSQL Application Program Interface to use in pandemic prediction. This research is funded by the Academy of Scientific Research and Technology (ASRT), Cairo, Egypt, project titled “Coronavirus Prevalence Prediction Model” (Project ID: 6641).
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
7
17
Boosted crossover for imbalanced medical datasets
Abeer S. Desuky
Prof. Assoc. in Math. Dept., Faculty of sciences Al-Azhar University
ABSTRACT
Due to the common use of electronic health databases in many healthcare services, healthcare data are available for classification researches in order to improve the quality of diseases diagnosis more efficiently. However, classification of healthcare-medical data is challenging because it is often imbalanced data. Most proposed algorithms are susceptible to classify the samples into the majority class, resulting in the insufficient prediction of minority class. In this paper, a preprocessing method is proposed, using boosted crossover to optimize the ratio of the two classes by progressively rebuilding the training dataset. This novel method is shown to give better performance than the existing popular methods.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
8
17
A Comparative Study Among the Main Categories of NoSQL Databases
Prof.Dr. Kamal ElDahshan , Dr. AbdAllah A. AlHabshy , Mr. Gaber Elsayed Abutaleb
Faculty of Science, Al-Azhar University, 11884, Nasr City, Cairo, Egypt
Faculty of Science, Al-Azhar University, 11884, Nasr City, Cairo, Egypt
Faculty of Science, Al-Azhar University, 11884, Nasr City, Cairo, Egypt .
ABSTRACT
A relational database is usually used to store and retrieve data. It is suitable when the volume of data is limited, but when it comes to big data, we need to use NoSQL (Not only SQL) databases; NoSQL databases were created to interact with large amounts of data. NoSQL databases provide many features such as scalability, availability, replication models, file sharing and schema-free. The main purpose of this paper is to present a comparative study of the five main categories of NoSQL databases. Namely, key-value stores, document stores, column family stores, graph stores databases, and object store NoSQL systems. Also, it mentions the famous database management systems for each one of these five categories. The comparison criteria used are performance, scalability, flexibility, complexity, and functionality. Moreover, this paper presents an overview of big data concepts. It briefly discusses the SQL databases versus NoSQL databases in terms of their high-level characteristics. Furthermore, this paper emphasizes the advantages and disadvantages of NoSQL databases. It illustrates the query languages in both SQL and NoSQL databases and represents the most common uses for each category to help users choose the most convenient DBMS for their organization.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
9
17
Comparative study Using Simulated Annealing Optimization Technique For Student Performance Prediction
Esraa A. Mahareek , Assoc.Prof. Abeer S. Desuky , Prof.Dr. Habiba Abdullah El-Zhni
demonstrator in Math. Dept., Faculty of sciences, Al-Azhar University
Prof. Assoc. in Math. Dept., Faculty of sciences Al-Azhar University
Emeritus Professor in Faculty of Science (Girls) Department of Mathematics Al-Azhar University
ABSTRACT
Understanding university students' performance and identifying factors that affect it. This issues are very important for educational institutions, educators, and students. To extract some meaningful information from these large volumes of data, academic organizations have to mine the data. For our comparative Process, we use three different datasets after the selection we preprocessed on the data, cleaned, and filtered the datasets, then we apply support vector machine(SVM) and compare the results with hybrid between it and simulated annealing optimization technique.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
10
17
Video Semantics Exploration for Indexing and Retrieval
استكشاف الفيديو دلالياً للفهرسة والإسترجاع
Kamal ElDahshan , Hesham Farouk , Amr Abozeid , Eslam Mofreh
Faculty of Science, Al-Azhar University, Nasr City, Cairo
Electronic Research Institute, Nozha, Cairo
Faculty of Science, Al Azhar University, Nasr City, Cairo
Faculty of Science, Al Azhar University, Nasr City, Cairo
ABSTRACT
Video semantic concepts exploration is a fundamental problem in a video indexing and retrieval. It has a long history of investigation since early days till recent achieved works. The challenges lie in bridging the gap between low level features and semantic level ones. To stand on the thoroughly situation, video semantic concepts exploration for indexing and retrieval purposes evolution from conventional methods to the state-of-the-art ones will be reviewed. The main contribution is to unify concepts involved and evolution in this interesting topic.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
11
17
Data and Task Management in ubiquitous computing environments: Review and Challenges
Ahmed. A. A. Gad-ElRab , M. S. Farag , T. A. A. Alzohairy , S. A. Yousef , Belal Z.Hassan
Vice Presidency for Development, King Abdulaziz University, Jeddah, Saudi Arabia (Home Address:Department of Mathematics Faculty of Science Al-Azhar University - Cairo, Egypt)
Department of Mathematics Faculty of Science Al-Azhar University - Cairo, Egypt
Department of Mathematics Faculty of Science Al-Azhar University - Cairo, Egypt
Department of Mathematics Faculty of Science Al-Azhar University - Cairo, Egypt
Department of Mathematics Faculty of Science Al-Azhar University - Cairo, Egypt
ABSTRACT
Currently, the human live is a world full of computing devices. By 2025; the number of smart device subscribers will reach 5.9 billion. Due to this increasing, computers are playing an ever-increasing role in people’s daily lives .As results, ubiquitous computing (UC) is a compelling vision for the future that is moving closer to realization at an accelerating pace. The key technologies that are required to make UC a reality is data and task management. Data lies at the heart of all UC applications, but these applications and environments impose new and challenging requirements for data and task management technologies. Most of the research and development activities in this area are focused on improving the devices themselves and on the technologies that are used in communications. For devices, the emphasis has been on improving functionality, while reducing size, cost, and power requirements. While, for communications, the emphasis has been on improving bandwidth and coverage, and on developing protocols that are more tolerant of the error and connectivity characteristics of wireless and mobile devices improved hardware and networking are clearly central to the development of UC, but an equally important and difficult set of challenges revolve around data and tasks management. In this paper, the key aspects of UC applications and environments from a data and task management perspective are identified. In addition, the challenges that face data and task management in UC environment such mobility, context awareness, collaboration will be described and discussed. Finally, some of existing solutions will be introduced in details.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
12
17
An Adaptive Data Fusion Scheme Using Graph Embedding in IoTs Environments
Ahmed. A. A. Gad-Elrab , Sawsan Mohammed Aziz , Heba F. Eid , Asmaa Mohamed fathy
Vice Presidency for Development, King Abdul-Aziz University, Jeddah, Saudi Arabia, (Home address: Department of Mathematics,Faculty Of Science, Al-Azhar University Cairo, Egypt)
Department of Mathematics,Faculty Of Science, Al-Azhar University, Cairo, Egypt
Department of Mathematics,Faculty Of Science, Al-Azhar University, Cairo, Egypt
Department of Mathematics,Faculty Of Science, Al-Azhar University, Cairo, Egypt
ABSTRACT
Recently, Internet of things (IoTs) is used for developing smart systems and architectures. In IoTs, the objects can be equipped with capabilities for identifying, sensing, networking and processing that will allow them to interact over the Internet with each other and with other devices and services to achieve some objectives. These sensing devices can collect and manage heterogeneous data that exist in their surrounding environments. This collected heterogeneous data is very big and needs high cost to be processed and transferred to a cloud server or a controlling center. In this case, it is better to fuse data before processing and transferring processes. The main problem in this scenario is the data fusion problem in order to allow highly reliable, effective and accurate management for decision-making in IoTs environments. To solve this problem, this paper proposes a new data fusion scheme, which based on using embedding data graph. This graph represents the similarities among data items. Based on this graph the data items can be divided into different groups and each group will be fused to minimize the amount of transferred data and latency time of the collected data and the energy consumption by IoTs devices. The results of conducted simulations show that the proposed data fusion scheme can achieve a good performance in terms of energy consumption, latency time, and data fusion accuracy compared to non-fusion schemes.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
13
17
An Ontology-based Arabic Named Entity Recognition System for
NLP-Storytelling
Marwa Mohammed Mamdouh Elgamal , Prof. Dr. Reda Abo Elezz , Mohammad T. Abou-Kreisha , Prof. Dr. Salwa Hamada
Faculty of Engineering, Systems & Computers Engineering Department, Al-Azhar University
Faculty of Engineering, Systems & Computers Engineering Department, Al-Azhar University
Faculty of Science,Mathematical Department , Al-Azhar University
Professor at National Research Institute, Cairo , Egypt
ABSTRACT
Background and challenges ontology is a representation model that defines domain knowledge with robust specifications that solve interoperability between human and machine. In this paper, we present an effective methodology for Arabic Storytelling ontology design and construction to extract domain ontology from unstructured Arabic story documents.
Motivations however, the manual building of ontologies is difficult and time-consuming process but ontology construction and learning which extracts ontological knowledge from various forms of data automatically or semi-automatically, can overcome the bottleneck of knowledge acquisition.
The objective of this paper is to investigate the problem of automatically construct and build Arabic storytelling ontology based on Arabic named entity recognition (NER) from unstructured story text.
Approach this paper presents a system that designed based on Machine Learning (ML) approach. The system framework is a combination of five main stages: First stage is determining the requirement analysis. Second document pre-processing using natural language processing (NLP) tasks. The third, is Conceptualization. The fourth stage is formal design and construction, the final stage is evaluation.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
14
17
New Trends in Deep Learning Based automatic translation system (ATS)
Prof.Dr.Reda Houssine Abo Alez , Prof.Dr.Mohamed fared Zaglol , Mohammad T. Abou-Kreisha , Dr.Assoc.Prof.Ahmad Almahdy , Eng.Dahey Gaber anem
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Mathematics,Faculty of science,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
ABSTRACT
Deep learning offers a way to join a large amount of computation and data with little engineering by hand. With distributed representation, various deep models have become the new state-of-the-art methods for solving an automatic translation system (ATS) problem. In this paper, we investigate the problems of the distributed representation of deep learning models and methods that have been employed for many deep neural automatic translation systems (DNATS). We contribute two novel neural models for learning such representations.
• For word-level representations, we propose Disambiguated Skip-gram (DSG): a neural network model for learning multi-sense word embedding. Representations learned by this model can be used in downstream tasks, like part-of-speech tagging or identification of semantic relations.
• For document-level representations, we propose Binary Paragraph Vector (BPV): a neural network model for learning binary representations of text documents, which can be used for fast document translation.
We provide a full evaluation of these models and demonstrate that they achieve the DNATS. We also report strong results in transfer learning settings, where our models are trained on a generic text corpus and then used to infer codes for documents from a domain-specific dataset.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
15
17
Performance Analysis Of Advanced Encryption Standard (AES) S-boxes
eng. Eslam wahba el said afify , Dr. Wageda I. El sobky , Dr. Abeer Twakol , Prof. Reda Abo Alez
Department of Electrical, Faculty of Engineering,Benha University Benha
Department of Mathematics Faculty of Engineering,Benha University Benha
Department of Electrical, Faculty of Engineering,Benha University Benha
Department of Systems and Computer Engineering Faculty of Engineering, Al Azhar University Cairo
ABSTRACT
The analysis of performance criteria for different cryptographic algorithms has increasingly been concerned in the last few years and that is because the majority of life applications need cryptographic algorithms to be involved in their structure to provide security for these applications such as banking services, e-government, and online applications. The Advanced Encryption Standard (AES) algorithm is available in many different encryption packages, and is the first (and only) publicly accessible cipher approved by the National Security Agency (NSA),The Rijndael S-box is a substitution box (lookup table) S-Box plays a major role in the AES algorithm security. The strength of S-Box depends on the design and algebraic constructions. This paper provides an overview of Advanced Encryption Standard AES S-Box analysis, the paper finds that algebraic attack is the most security hole of AES S-Box, also give an idea about different previous research to improve the static S-boxes that has been used in AES, to enhance the strength of AES Performance by appalling the best S-box.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
16
17
Text translation and post-editing and revision with Document Embedding
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Mathematics,Faculty of science,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
ABSTRACT
Distributed representations have gained a lot of interest in the Text translation and post-editing and revision public. In this paper, we propose a method to learn document embedding for text translation and post-editing and revision tasks. In our architecture, each document can be represented as a fine-grained representation of different meanings so that the Text translation and post-editing and revision can be done more accurately. The results of our experiments show that our method achieves better performances on our datasets.
Code
BOT
MATH
STA
CSC
CHEM
GEO
BIO
ASM
PHY
10th International Scientific Conf.
Basic Sciences and its Applications
30 March – 1 April, 2020
Cairo, Egypt
المؤتمر العلمي الدولي العاشر
العلوم الأساسية وتطبيقاتها
2020
ابريل
1
-
مارس
30
القاهرة ـ جمهورية مصر العربية
Computer Science and its applications
17
17
Statistical automatic translation system (SATS) versus
Neural automatic translation system (NATS)
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Mathematics,Faculty of science,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
Department of Systems Engineering and Computers,Faculty of Engineering,Al-Azhar University,egypt
ABSTRACT
In this paper, we provide a comparison of the Statistical automatic translation system (SATS) and neural machine translation (NATS) for German to Arabic (GR-AR) in the fixed field. We discuss the challenges for SATS and NATS of a less-resourced language such as Arabic and show that while the NATS system may not cost equally as well as the SATS system, the future may still be hopeful for (GR-AR) NATS.
