Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300102
N. Mirza
In recent times, robotics and especially soft robotics has attracted a wide range of researchers and scientists. As oft robotics has an extensive number of advantages in the real environment, due to their less complex system and cost. Soft grippers are more adaptive as compared to the rigid robotic grippers. The grasping performance of soft robots can be improved without bringing major changes in the control inputs. Machine learning has played a vital role in improving the controls and increasing the number of applications of these kinds of robots in the real world. In this paper relevant research in modeling, design, intelligent control, sensing, and practical applications of soft robots has been discussed.
{"title":"Machine Learning and Soft Robotics","authors":"N. Mirza","doi":"10.1109/ACIT50332.2020.9300102","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300102","url":null,"abstract":"In recent times, robotics and especially soft robotics has attracted a wide range of researchers and scientists. As oft robotics has an extensive number of advantages in the real environment, due to their less complex system and cost. Soft grippers are more adaptive as compared to the rigid robotic grippers. The grasping performance of soft robots can be improved without bringing major changes in the control inputs. Machine learning has played a vital role in improving the controls and increasing the number of applications of these kinds of robots in the real world. In this paper relevant research in modeling, design, intelligent control, sensing, and practical applications of soft robots has been discussed.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115019446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300110
B. Sarada, M. Dandu, S. Tarun
In this paper, we empirically analyze and compare the performance of neural network-based classification (MLP) and decision tree based classifications (CART and Random Tree) on data sets with banking and medical purpose information. We included structural parameters for distinguishing the classification methods. We also introduced up sampling and down sampling along with feature selection and found a more detailed analysis of the Precision, Recall, F1 score, Area under the Curve, Test and Train accuracies which are necessary in order to judge the performance of the learning and classification method of all the models. However, we identified some limitations involved with these sampling techniques during the research such as loss of vital data and overfitting outcomes.
{"title":"Comparison of Tree Based Classifications and Neural Network Based Classification","authors":"B. Sarada, M. Dandu, S. Tarun","doi":"10.1109/ACIT50332.2020.9300110","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300110","url":null,"abstract":"In this paper, we empirically analyze and compare the performance of neural network-based classification (MLP) and decision tree based classifications (CART and Random Tree) on data sets with banking and medical purpose information. We included structural parameters for distinguishing the classification methods. We also introduced up sampling and down sampling along with feature selection and found a more detailed analysis of the Precision, Recall, F1 score, Area under the Curve, Test and Train accuracies which are necessary in order to judge the performance of the learning and classification method of all the models. However, we identified some limitations involved with these sampling techniques during the research such as loss of vital data and overfitting outcomes.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125335979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300048
F. Bessai-Mechmache, Karima Hammouche, Z. Alimazighi
Finding the valuable relevant information continues to be the major challenges of Information Retrieval Systems owing to the explosive growth of online web information. Among these challenges, we consider the XML Information Retrieval challenges as XML has become a de facto standard over the Web. In this paper, we tackle the issue of content-based XML information retrieval. We formulate the retrieval issue as a combinatorial optimization problem in order to generate the best set of relevant XML elements for a given keywords query. In our proposal, we define a genetic algorithm which maximizes similarity between a set of XML elements and the user query. The results based on the precision measure are very promising.
{"title":"A Genetic Algorithm-Based XML Information Retrieval Model","authors":"F. Bessai-Mechmache, Karima Hammouche, Z. Alimazighi","doi":"10.1109/ACIT50332.2020.9300048","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300048","url":null,"abstract":"Finding the valuable relevant information continues to be the major challenges of Information Retrieval Systems owing to the explosive growth of online web information. Among these challenges, we consider the XML Information Retrieval challenges as XML has become a de facto standard over the Web. In this paper, we tackle the issue of content-based XML information retrieval. We formulate the retrieval issue as a combinatorial optimization problem in order to generate the best set of relevant XML elements for a given keywords query. In our proposal, we define a genetic algorithm which maximizes similarity between a set of XML elements and the user query. The results based on the precision measure are very promising.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121822701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300057
Jennifer Batamuliza, D. Hanyurwimfura
Smart Grid uses modern metering electricity and some devices that collect energy data in a real time manner and send the clients usage report of electricity usage to the service provider. The service provider uses the received data for billing the client or other services. Through this smart grid, the daily energy consumption and devices that are being used by home owner can be predicted by the service provider depending on how electricity is consumed. This can lead to security issues security where hackers can easily capture clients data while it's being transferred to the service provider. The hacker can modify the transmitted data and the services provider will receive the wrong data. This paper introduces a key distribution system that is more efficient and secure. Existing identity based encryption and identity based signature schemes for smart grid have key escrow problem. In this paper we introduce a certificateless signcryption for key distribution scheme which is more efficient and secure than the existing schemes. It allows for both decryption and verification by authorized users, provide Key Generation Center to only partial key and provide low computation and communication cost compared with existing works. The proposed scheme also achieves key escrow resilience unlike previous works in this field.
{"title":"A secure and efficient anonymous certificateless signcryption for Key Distribution Scheme for Smart Grid","authors":"Jennifer Batamuliza, D. Hanyurwimfura","doi":"10.1109/ACIT50332.2020.9300057","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300057","url":null,"abstract":"Smart Grid uses modern metering electricity and some devices that collect energy data in a real time manner and send the clients usage report of electricity usage to the service provider. The service provider uses the received data for billing the client or other services. Through this smart grid, the daily energy consumption and devices that are being used by home owner can be predicted by the service provider depending on how electricity is consumed. This can lead to security issues security where hackers can easily capture clients data while it's being transferred to the service provider. The hacker can modify the transmitted data and the services provider will receive the wrong data. This paper introduces a key distribution system that is more efficient and secure. Existing identity based encryption and identity based signature schemes for smart grid have key escrow problem. In this paper we introduce a certificateless signcryption for key distribution scheme which is more efficient and secure than the existing schemes. It allows for both decryption and verification by authorized users, provide Key Generation Center to only partial key and provide low computation and communication cost compared with existing works. The proposed scheme also achieves key escrow resilience unlike previous works in this field.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126924251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300097
Kayal Padmanandam, Lakshmi Lingutla
The advent of IoT has brought in a huge amount of data that is exponentially growing every second. This seemingly growing data has paved the way to rethink on various technologies to capture the data and analyze it properly. Such huge data is the fuel for various analytics and intelligent systems like machine learning and deep learning applications. The deployment of machine learning and deep learning intelligence across the analytical network takes place in the central data system (cloud servers) which is a very expensive challenge in terms of time, money, data privacy. But the application of such intelligence at the edge computing, which is a new paradigm of the cloud-enabled network, has solved the problem by offering high security and reliability. Unlike Cloud computing, edge computing is a decentralized, distributed architecture where analytics and insight happens near or at the data source itself that solves the expensive challenges mentioned above. This paper describes the network of edge computing and its variance from cloud computing, edge architecture, and diverse applications of machine learning algorithms and deep learning framework deployed at the edge network for intelligent analytics.
{"title":"Practice of Applied Edge Analytics in Intelligent Learning Framework","authors":"Kayal Padmanandam, Lakshmi Lingutla","doi":"10.1109/ACIT50332.2020.9300097","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300097","url":null,"abstract":"The advent of IoT has brought in a huge amount of data that is exponentially growing every second. This seemingly growing data has paved the way to rethink on various technologies to capture the data and analyze it properly. Such huge data is the fuel for various analytics and intelligent systems like machine learning and deep learning applications. The deployment of machine learning and deep learning intelligence across the analytical network takes place in the central data system (cloud servers) which is a very expensive challenge in terms of time, money, data privacy. But the application of such intelligence at the edge computing, which is a new paradigm of the cloud-enabled network, has solved the problem by offering high security and reliability. Unlike Cloud computing, edge computing is a decentralized, distributed architecture where analytics and insight happens near or at the data source itself that solves the expensive challenges mentioned above. This paper describes the network of edge computing and its variance from cloud computing, edge architecture, and diverse applications of machine learning algorithms and deep learning framework deployed at the edge network for intelligent analytics.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125519351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300122
Aya Mourad, A. Afifi, A. Keshk
Brain tumor segmentation is a challenging task due to the strong fluctuation in intensity and shape. It has attracted the attention of medical imaging community for several years. This work introduces a fully automated brain tumor segmentation approach from multimodal MRI images. Segmentation in three different MRI modalities; T1 (gadolinium-enhanced), T2, and Fluid-Attenuated Inversion-Recovery (FLAIR) are compared to choose the best one. The proposed approach utilizes a super-pixel over-segmentation technique and applying a classification for each super-pixel which leads to more smooth segmentation. Several features including statistical, fractal, and texture features are calculated from each super-pixel of the normalized (T1, T2, and flair) images to ensure a robust classification. Additionally, the class imbalance problem is tackled to allow the algorithm to accurately segment abnormal tissue. The Random Forest (RF) classification algorithm is utilized for final segmentation. The RF classifier is being chosen in the proposed approach because it provides a better performance according to the confusion matrix results. The proposed approach has been trained using 10 Low-Grade and 20 High-Grade cases and evaluated using different 5 Low-Grade and 5 High-Grade cases from BRATS 2013 dataset. Dice, average precision, sensitivity, and F1-score metrics are used for segmentation accuracy evaluation. The average precision, sensitivity, fl-score and dice overlap for tumor segmentation are 92%, 95%, 96% and 94% for flair images, 89%, 92%, 90% and 93% for T2 and 89%, 90%, 89% and 90% for T1. Finally, the voting strategy is being used to get the best segmentation between these different modalities.
{"title":"Automated Brain Tumor Segmentation in MRI using Superpixel Over-segmentation and Classification","authors":"Aya Mourad, A. Afifi, A. Keshk","doi":"10.1109/ACIT50332.2020.9300122","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300122","url":null,"abstract":"Brain tumor segmentation is a challenging task due to the strong fluctuation in intensity and shape. It has attracted the attention of medical imaging community for several years. This work introduces a fully automated brain tumor segmentation approach from multimodal MRI images. Segmentation in three different MRI modalities; T1 (gadolinium-enhanced), T2, and Fluid-Attenuated Inversion-Recovery (FLAIR) are compared to choose the best one. The proposed approach utilizes a super-pixel over-segmentation technique and applying a classification for each super-pixel which leads to more smooth segmentation. Several features including statistical, fractal, and texture features are calculated from each super-pixel of the normalized (T1, T2, and flair) images to ensure a robust classification. Additionally, the class imbalance problem is tackled to allow the algorithm to accurately segment abnormal tissue. The Random Forest (RF) classification algorithm is utilized for final segmentation. The RF classifier is being chosen in the proposed approach because it provides a better performance according to the confusion matrix results. The proposed approach has been trained using 10 Low-Grade and 20 High-Grade cases and evaluated using different 5 Low-Grade and 5 High-Grade cases from BRATS 2013 dataset. Dice, average precision, sensitivity, and F1-score metrics are used for segmentation accuracy evaluation. The average precision, sensitivity, fl-score and dice overlap for tumor segmentation are 92%, 95%, 96% and 94% for flair images, 89%, 92%, 90% and 93% for T2 and 89%, 90%, 89% and 90% for T1. Finally, the voting strategy is being used to get the best segmentation between these different modalities.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131416730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300051
Younes-aziz Bachiri, H. Mouncif
The university must adapt to the challenges which have characterized the 21st century. According to UNESCO, during the period of the COVID-19 pandemic the number of learners has been affected by school closures; it has exceeded 1.5 billion in 195 countries. The Sultan Moulay Slimane University in Morocco has employed a strategy through distance education which makes the online courses massive and open to all, but there are many obstacles such as the problem of choice due to the diversity of platforms and multilingual e-assessment tools. To solve this serious problem, we have thought of establishing criteria for choosing a suitable learning management system and integrating new automatic natural language processing, using artificial intelligence techniques to make MOOCs more attractive. To do this, we created a plugin of automatic multilingual questions generation which transforms the course into an addictive game with points and badges. To solve this serious problem, we have thought of establishing criteria for choosing a suitable learning management system and integrating new automatic natural language processing, using artificial intelligence techniques to make MOOCs more attractive. To do this, we created a plugin of automatic multilingual questions generation which transforms the course into an addictive game with points and badges.
{"title":"Applicable strategy to choose and deploy a MOOC platform with multilingual AQG feature","authors":"Younes-aziz Bachiri, H. Mouncif","doi":"10.1109/ACIT50332.2020.9300051","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300051","url":null,"abstract":"The university must adapt to the challenges which have characterized the 21st century. According to UNESCO, during the period of the COVID-19 pandemic the number of learners has been affected by school closures; it has exceeded 1.5 billion in 195 countries. The Sultan Moulay Slimane University in Morocco has employed a strategy through distance education which makes the online courses massive and open to all, but there are many obstacles such as the problem of choice due to the diversity of platforms and multilingual e-assessment tools. To solve this serious problem, we have thought of establishing criteria for choosing a suitable learning management system and integrating new automatic natural language processing, using artificial intelligence techniques to make MOOCs more attractive. To do this, we created a plugin of automatic multilingual questions generation which transforms the course into an addictive game with points and badges. To solve this serious problem, we have thought of establishing criteria for choosing a suitable learning management system and integrating new automatic natural language processing, using artificial intelligence techniques to make MOOCs more attractive. To do this, we created a plugin of automatic multilingual questions generation which transforms the course into an addictive game with points and badges.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133127039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9299966
Maria Khan, G. Rasool
The benefits of design patterns to solve recurring and generic problems is well known for the software industry and academia. Game design patterns are being introduced to solve the particular type of problems for the development of computer games. The formal and informal specifications of game design patterns exist because of differences in implementation, design requirements and programming languages. We analyzed the state of the art related to mobile game design patterns and realized that mobile applications are developed by using mobile game design patterns for the development of quality software applications. The recovery of mobile game design patterns is helpful for the comprehension, reverse engineering, maintenance, evolution and refactoring of software applications. The contribution of this paper are specification and detection of 10 mobile game design patterns from 8 open source mobile games. A prototyping tool is developed to demonstrate the concept of the approach. We evaluate our approach by using precision, recall and F-measure metrics.
{"title":"Recovery of Mobile Game Design Patterns","authors":"Maria Khan, G. Rasool","doi":"10.1109/ACIT50332.2020.9299966","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9299966","url":null,"abstract":"The benefits of design patterns to solve recurring and generic problems is well known for the software industry and academia. Game design patterns are being introduced to solve the particular type of problems for the development of computer games. The formal and informal specifications of game design patterns exist because of differences in implementation, design requirements and programming languages. We analyzed the state of the art related to mobile game design patterns and realized that mobile applications are developed by using mobile game design patterns for the development of quality software applications. The recovery of mobile game design patterns is helpful for the comprehension, reverse engineering, maintenance, evolution and refactoring of software applications. The contribution of this paper are specification and detection of 10 mobile game design patterns from 8 open source mobile games. A prototyping tool is developed to demonstrate the concept of the approach. We evaluate our approach by using precision, recall and F-measure metrics.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116977863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300085
M. Eltahan, Karim Moharm, Nour Daoud
Exact forecast of surface temperature over MARS is important and critical. Surface temperature is fundamental to the environmental parameter that has a direct impact on designing and operating the land rovers that explore the MARS planet. In this paper, We used well known long Short-Term Memory (LSTM) algorithm to build a data-driven model to predict the surface temperature over the planned landing site Jezero Crater for Mars 2020 Rover. The data-driven model is built using a dataset based on the Mars Climate Database (MCD) which derived from the Global Climate Model (GCM) simulations for MARS. The temporal availability of this data from martian year 24 to 33. we evaluated the effect of the three different optimization solvers on surface temperature prediction over the landing site Jezero Crater for two different numbers of epochs. The solver that provides the lowest RMSE is used to predict the surface temperature over the landing site from martian year 34 to martian year 36.
{"title":"Sensitivity of different optimization solvers in LSTM algorithm for temperature forecast over Mars at Jezero Crater landing site","authors":"M. Eltahan, Karim Moharm, Nour Daoud","doi":"10.1109/ACIT50332.2020.9300085","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300085","url":null,"abstract":"Exact forecast of surface temperature over MARS is important and critical. Surface temperature is fundamental to the environmental parameter that has a direct impact on designing and operating the land rovers that explore the MARS planet. In this paper, We used well known long Short-Term Memory (LSTM) algorithm to build a data-driven model to predict the surface temperature over the planned landing site Jezero Crater for Mars 2020 Rover. The data-driven model is built using a dataset based on the Mars Climate Database (MCD) which derived from the Global Climate Model (GCM) simulations for MARS. The temporal availability of this data from martian year 24 to 33. we evaluated the effect of the three different optimization solvers on surface temperature prediction over the landing site Jezero Crater for two different numbers of epochs. The solver that provides the lowest RMSE is used to predict the surface temperature over the landing site from martian year 34 to martian year 36.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117088208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300100
Dana Halabi, A. Awajan, Ebaa Fayyoumi
Arabic dependency parsers perform poorly compared to parsers of other languages. There is little research on improving the performance of Arabic parsers. However, recent research has shown slight improvements in the performance of dependency parsers by utilizing the lexical level of a dependency treebank. To our knowledge, no previous study has studied the effect of utilizing the syntactic level. In this study, we empirically investigated the impact of varying the set of dependency relations on the performance of Arabic dependency parsers. The results were compared to those of previous studies, and showed that having an appropriate set of dependency relations could improve the performance of an Arabic dependency parser.
{"title":"Improving Arabic dependency parsers by using dependency relations","authors":"Dana Halabi, A. Awajan, Ebaa Fayyoumi","doi":"10.1109/ACIT50332.2020.9300100","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300100","url":null,"abstract":"Arabic dependency parsers perform poorly compared to parsers of other languages. There is little research on improving the performance of Arabic parsers. However, recent research has shown slight improvements in the performance of dependency parsers by utilizing the lexical level of a dependency treebank. To our knowledge, no previous study has studied the effect of utilizing the syntactic level. In this study, we empirically investigated the impact of varying the set of dependency relations on the performance of Arabic dependency parsers. The results were compared to those of previous studies, and showed that having an appropriate set of dependency relations could improve the performance of an Arabic dependency parser.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127368139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：