Education

1. MSc (Computer Science), Satbayev University, 2021
   Supervisor: Prof. Daniyar Borisovich Nurseitov
   Thesis: Attention-based fully gated cnn-bgru for russian handwritten text

2. Course Based Master (Computer Science), Assiut University, Egypt, 2017
   

3. BSc (Computer Science), Assiut University, Egypt, 2015

Research interests

• Natural Language Processing:
  • Information Retrieval
  • Few shot Learning
  • Zero shot
  • Text Ranking
  • Open-domain Question Answering
  • Keyword Information Extraction
  • Text Generation
  • Large Language Model
• Computer Vision:
  • Self-supervised learning (SSL)
  • Object detection
  • Generative Adversarial Network
  • Segmentation
  • Handwritten
  • OCR
  • Image Retrieval
  • Image Processing

Publications

• IHRRB-DINO: Identifying High-Risk Regions of Breast Masses in Mammogram Images Using Data-Driven Instance Noise (DINO)
  Mahmoud K., Abdelrahman A., Ibrahim A., Norah A., Sohail C., Ayman E.
  Equal contribution: Mahmoud K., Abdelrahman A. and Ibrahim A.
  MICCAI 2024
  PDF | Link | Bibtex

  @InProceedings{101007978-3-031-72378-0_11, author="Kasem, Mahmoud SalahEldin and Abdallah, Abdelrahman and Abdelhalim, Ibrahim and Alghamdi, Norah Saleh and Contractor, Sohail and El-Baz, Ayman", editor="Linguraru, Marius George and Dou, Qi and Feragen, Aasa and Giannarou, Stamatia and Glocker, Ben and Lekadir, Karim and Schnabel, Julia A.", title="IHRRB-DINO: Identifying High-Risk Regions of Breast Masses in Mammogram Images Using Data-Driven Instance Noise (DINO)", booktitle="Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024", year="2024", publisher="Springer Nature Switzerland", address="Cham", pages="113--122", abstract="In this paper, we introduce IHRRB-DINO, an advanced model designed to assist radiologists in effectively detecting breast masses in mammogram images. This tool is specifically engineered to highlight high-risk regions, enhancing the capability of radiologists in identifying breast masses for more accurate and efficient assessments. Our approach incorporates a novel technique that employs Data-Driven Instance Noise (DINO) for Object Localization, which significantly improves breast mass localization. This method is augmented by data augmentation using instance-level noise during the training phase, focusing on refining the model's proficiency in precisely localizing breast masses in mammographic images. Rigorous testing and validation conducted on the BI-RADS dataset using our model, especially with the Swin-L backbone, have demonstrated promising results. We achieved an Average Precision (AP) of 46.96, indicating a substantial improvement in the accuracy and consistency of breast cancer (BC) detection and localization. These results underscore the potential of IHRRB-DINO in contributing to the advancements in computer-aided diagnosis systems for breast cancer, marking a significant stride in the field of medical imaging technology.", isbn="978-3-031-72378-0" }

• Detecting Temporal Ambiguity in Questions
  Bhawna P., Abdelrahman A., Jamshid M., Adam J.
  EMNLP Findings 2024
  PDF | Link | Code & Data| Bibtex

  @article{piryani2024detecting, title={Detecting Temporal Ambiguity in Questions}, author={Piryani, Bhawna and Abdallah, Abdelrahman and Mozafari, Jamshid and Jatowt, Adam}, journal={arXiv preprint arXiv:2409.17046}, year={2024} }

• Exploring Hint Generation Approaches in Open-Domain Question Answering
  Jamshid M., Abdelrahman A., Bhawna P., Adam J.
  EMNLP Findings 2024
  PDF | Link | Code & Data| Bibtex

  @article{mozafari2024exploring, title={Exploring Hint Generation Approaches in Open-Domain Question Answering}, author={Mozafari, Jamshid and Abdallah, Abdelrahman and Piryani, Bhawna and Jatowt, Adam}, journal={arXiv preprint arXiv:2409.16096}, year={2024} }

• ArabicaQA: A Comprehensive Dataset for Arabic Question Answering
  Abdelrahman A., Mahmoud K., Mahmoud A.,Mohamed M., Mohamed E., Yasser E., Adam J.
  SIGIR , 2024
  PDF | Link | Code & Data| Bibtex

  @misc{abdallah2024arabicaqa, title={ArabicaQA: A Comprehensive Dataset for Arabic Question Answering}, author={Abdelrahman Abdallah and Mahmoud Kasem and Mahmoud Abdalla and Mohamed Mahmoud and Mohamed Elkasaby and Yasser Elbendary and Adam Jatowt}, year={2024}, eprint={2403.17848}, archivePrefix={arXiv}, primaryClass={cs.CL} }

• Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis
  Abdelrahman A., Eberharter D., Pfister Z., Yasser E, Adam J.
  arXiv , 2024
  PDF | Link | Bibtex

  @article{abdallah2024transformers, title={Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis}, author={Abdallah, Abdelrahman and Eberharter, Daniel and Pfister, Zoe and Jatowt, Adam}, journal={arXiv preprint arXiv:2403.04080}, year={2024} }

• AMuRD: Annotated Multilingual Receipts Dataset for Cross-lingual Key Information Extraction and Classification
  Abdelrahman A., Mahmoud A., Mohamed E., Yasser E., Adam J.
  arXiv , 2023
  PDF | Link | Code & Data | Bibtex

  @misc{abdallah2023amurd, title={AMuRD: Annotated Multilingual Receipts Dataset for Cross-lingual Key Information Extraction and Classification}, author={Abdelrahman Abdallah and Mahmoud Abdalla and Mohamed Elkasaby and Yasser Elbendary and Adam Jatowt}, year={2023}, eprint={2309.09800}, archivePrefix={arXiv}, primaryClass={cs.CL} }

• Generator-Retriever-Generator: A Novel Approach to Open-domain Question Answering
  Abdelrahman A., Adam J.
  arXiv , 2023
  PDF | Link | Code & Data | Bibtex

  @article{abdallah2023generator, title={Generator-Retriever-Generator: A Novel Approach to Open-domain Question Answering}, author={Abdallah, Abdelrahman and Jatowt, Adam}, journal={arXiv preprint arXiv:2307.11278}, year={2023} }

• Exploring the State of the Art in Legal QA Systems
  Abdelrahman A., Bhawna P., Adam J.
  Journal of Big Data , 2023
  PDF | Link | Code & Data | Bibtex

  @misc{abdallah2023exploring, title={Exploring the State of the Art in Legal QA Systems}, author={Abdelrahman Abdallah and Bhawna Piryani and Adam Jatowt}, year={2023}, eprint={2304.06623}, archivePrefix={arXiv}, primaryClass={cs.CL} }

• Deep learning for table detection and structure recognition: A survey
  Mahmoud K., Abdelrahman A., Alexander B., Ebrahem E., Mahmoud A., Mohamed M., Mohamed H., Daniyar N., Islam T.
  arXiv , 2023
  PDF | Link | Code & Data | Bibtex

  @misc{abdallah2023exploring, doi = {10.48550/ARXIV.2211.08469}, url = {https://arxiv.org/abs/2211.08469}, author = {Kasem, Mahmoud and Abdallah, Abdelrahman and Berendeyev, Alexander and Elkady, Ebrahem and Abdalla, Mahmoud and Mahmoud, Mohamed and Hamada, Mohamed and Nurseitov, Daniyar and Taj-Eddin, Islam}, keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Deep learning for table detection and structure recognition: A survey}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} }

• TNCR: Table net detection and classification dataset
  Abdelrahman A., Alexander B., Islam N., Daniyar N.
  Neurocomputing, 2022
  PDF | Link | Code & Data | Bibtex

  @article{abdallah2022tncr, title={TNCR: Table net detection and classification dataset}, author={Abdallah, Abdelrahman and Berendeyev, Alexander and Nuradin, Islam and Nurseitov, Daniyar}, journal={Neurocomputing}, volume={473}, pages={79--97}, year={2022}, publisher={Elsevier} }

• KOHTD: Kazakh offline handwritten text dataset
  Nazgul T., Mahmoud K., Galymzhan A., Kairat B., Abdelrahman A., Anel A., Daniyar N.
  Signal Processing: Image Communication, 2022
  PDF | Link | Code & Data | Bibtex

  @article{toiganbayeva2022kohtd, title={Kohtd: Kazakh offline handwritten text dataset}, author={Toiganbayeva, Nazgul and Kasem, Mahmoud and Abdimanap, Galymzhan and Bostanbekov, Kairat and Abdallah, Abdelrahman and Alimova, Anel and Nurseitov, Daniyar}, journal={Signal Processing: Image Communication}, volume={108}, pages={116827}, year={2022}, publisher={Elsevier} }

• Attention-based fully gated CNN-BGRU for russian handwritten text
  Abdelrahman A., Mohamed H., Daniyar N.
  Journal of Imaging, 2020
  PDF | Link | Bibtex

  @article{abdallah2020attention, title={Attention-based fully gated cnn-bgru for russian handwritten text}, author={Abdallah, Abdelrahman and Hamada, Mohamed and Nurseitov, Daniyar}, journal={Journal of Imaging}, volume={6}, number={12}, pages={141}, year={2020}, publisher={MDPI} }

• Handwritten Kazakh and Russian (HKR) database for text recognition
  Daniyar N., Kairat B., Daniyar K., Anel A., Abdelrahman A., Rassul Tolegenov
  Multimedia Tools and Applications, 2021
  PDF | Link | Code & Data | Bibtex

  @article{nurseitov2021handwritten, title={Handwritten Kazakh and Russian (HKR) database for text recognition}, author={Nurseitov, Daniyar and Bostanbekov, Kairat and Kurmankhojayev, Daniyar and Alimova, Anel and Abdallah, Abdelrahman and Tolegenov, Rassul}, journal={Multimedia Tools and Applications}, volume={80}, number={21}, pages={33075--33097}, year={2021}, publisher={Springer} }

• Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
  Daniyar N., Kairat B., Maksat K., Anel A., Abdelrahman A., Galymzhan A.
  Advances in Science, Technology and Engineering Systems Journal (ASTESJ), 2020
  PDF | Link | Bibtex

  @article{DaniyarNurseitovKairatBostanbekovMaksatKanatovAnelAlimovaAbdelrahmanAbdallah2020, author = {{Daniyar Nurseitov, Kairat Bostanbekov, Maksat Kanatov, Anel Alimova, Abdelrahman Abdallah}, Galymzhan Abdimanap}, doi = {10.25046/aj0505114}, file = {:D$\backslash$:/ASTESJ/ASTESJ{\_}0505114.pdf:pdf}, journal = {Advances in Science, Technology and Engineering Systems Journal}, keywords = {CNN,CTC,Convolutional neural networks,RNN,Recurrent neural networks}, number = {5}, pages = {934--943}, title = {{Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models}}, volume = {5}, year = {2020} }

• Automated Question Answer medical model based on Deep Learning Technology
  Abdelrahman A., Mahmoud K., Mohamed H., Shaymaa S.
  ICEMIS'20: Proceedings of the 6th International Conference on Engineering & MIS, 2020
  PDF | Link | Bibtex

  @inproceedings{abdallah2020automated, title={Automated question-answer medical model based on deep learning technology}, author={Abdallah, Abdelrahman and Kasem, Mahmoud and Hamada, Mohamed A and Sdeek, Shaymaa}, booktitle={Proceedings of the 6th International Conference on Engineering \& MIS 2020}, pages={1--8}, year={2020} }

• Neural network estimation model to optimize timing and schedule of software projects
  Mohamed A. H., Abdelrahman A., Mahmoud K., Mohamed A.
  2021 IEEE International Conference on Smart Information Systems and Technologies (SIST), 2021
  Link | Bibtex

  @inproceedings{hamada2021neural, title={Neural network estimation model to optimize timing and schedule of software projects}, author={Hamada, Mohamed A and Abdallah, Abdelrahman and Kasem, Mahmoud and Abokhalil, Mohamed}, booktitle={2021 IEEE International Conference on Smart Information Systems and Technologies (SIST)}, pages={1--7}, year={2021}, organization={IEEE} }

• AE-LSTM: Autoencoder with LSTM-Based Intrusion Detection in IoT
  Mohamed M., Mahmoud K., Abdelrahman A., Hyun S. K.
  2022 International Telecommunications Conference (ITC-Egypt), 2022
  Link | Bibtex

  @inproceedings{mahmoud2022ae, title={AE-LSTM: Autoencoder with LSTM-Based Intrusion Detection in IoT}, author={Mahmoud, Mohamed and Kasem, Mahmoud and Abdallah, Abdelrahman and Kang, Hyun Soo}, booktitle={2022 International Telecommunications Conference (ITC-Egypt)}, pages={1--6}, year={2022}, organization={IEEE} }

• Enhancing Core Image Classification Using Generative Adversarial Networks (GANs)
  Galymzhan A., Kairat B., Abdelrahman A. , Anel A., Darkhan K., Daniyar N.
  arXiv, 2022
  PDF | Link | Bibtex

  @article{nurseitov2022application, title={Enhancing Core Image Classification Using Generative Adversarial Networks (GANs) }, author={Nurseitov, Daniyar and Bostanbekov, Kairat and Abdimanap, Galymzhan and Abdallah, Abdelrahman and Alimova, Anel and Kurmangaliyev, Darkhan}, journal={arXiv preprint arXiv:2204.14224}, year={2022} }

• Developing Predictive Oil Well Diagnostics Based on Intelligent Algorithms
  Zhanar O., Daur A., Aslan A., Abdelrahman A.
  2021 IEEE International Conference on Smart Information Systems and Technologies (SIST), 2021
  PDF | Link | Bibtex

  @inproceedings{omirbekova2021developing, title={Developing Predictive Oil Well Diagnostics Based on Intelligent Algorithms}, author={Omirbekova, Zhanar and Aktaukenov, Daur and Amangeldiyev, Aslan and Abdallah, Abdelrahman}, booktitle={2021 IEEE International Conference on Smart Information Systems and Technologies (SIST)}, pages={1--7}, year={2021}, organization={IEEE} }

Experience

• Dec. 2022 - Now
  Researcher Assistant, Digital Science Center (DiSC), Universität Innsbruck, Innsbruck, Austria

• Aug. 2021 - Now
  Machine Learning Engineering (part-time), DISCO AI, Cairo, Egypt

• Jan. 2022 - Dec. 2022
  Machine Learning Researcher, Università Ca' Foscari, Venezia, Italy

• Aug. 2021 - June. 2022
  Machine Learning Engineering, KMG Engineering, Nur-Sultan, Kazakhstan

• 2019 - 2021
  Machine Learning Researcher, National Open Research Laboratory for Information and Space Technologies, Satbayev University, Almaty, Kazakhstan

• 2021 - 2022
  Assistant Lecturer, Computer Science, Assiut University, Egypt

• 2019 - 2019
  Software Developer, Ccc at limkokwing university, - Cyberjaya, Malaysia

• 2015 - 2019
  Research and Teaching Assistant, Computer Science, Assiut University, Egypt

• 2016 - 2017
  Web Developer FastKood Company, Cario, Egypt

• 2015 - 2016
  Software Developer, Overcoffeesolutions, Assiut, Egypt

Awards

• 2019 - 2021
  Research Scholarship, Satbayev University

• 2021
  Best Master Thesis Award, Satbayev University, Kazakhstan

Reviwer

Conferences

• SIGIR 2024
• LREC-COLING 2024
• WACV2023
• EMNLP 2023

Journals

• Pattern Recognition Letters
  
• IET NBT Transition
  
• Heliyon
  
• IET Signal Processing