Md Ataur Rahman

Md Ataur Rahman


I am an NLP/ML enthusiast with a background in Computer Science and Computational Linguistics. In my spare time, I enjoy watching lectures of Freeman Dyson, Richard Feynman and Andrew Ng.


·        M.A. in Computational Linguistics (Research Masters), University of Groningen, The Netherlands.

·        M.Sc. in Language Science and TechnologySaarland University, Germany.
                • Thesis: "Exploring Features for Multi-label Hate Speech Detection"

  • B.Sc. Engineering in Computer Science and Engineering

·        Dept. of Computer Science and Engineering, University of Chittagong.
                • Thesis: "Extraction of Opinion and Aspect from Corpus Based Reviews"



July 2015 – Present

  • Faculty Member, Department of Computer Science and Engineering.
    Premier University, Chittagong (Bangladesh).

Nov 2014 – June 2015

  • Software Engineer, Bit Mascot (Pvt.) Ltd, Dhaka (Bangladesh).
    Key Responsibility: iOS Application Developer.


Area of Interests

  • Theoretical: Language of Thought, Representational Theories of Consciousness, Compositional Semantics, Computational Distributional Semantics.

  • Practical: Handwritten Text Recognition, Knowledge Graphs, Data Integration, Polarity Items & Sentiment Shifters, Machine Learning, Natural Language Processing.

GitHub:     link


Award & Prizes

  • 2021:    Marie Skłodowska-Curie Ph.D. Fellowship under Horizon 2020 (H2020-MSCA-ITN-2020) framework - The European Joint Doctorate Program in "Data Engineering for Data Science" (DEDS). 
  • 2019:    1st position for German and 2nd and 3rd position for Hindi Multiclass Hate Speech classification on “Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC)” Shared Task 2019”.
  • 2019:    FIRE 2019 Student Grant for the top-performing systems in HASOC Task A and Task B.
  • 2017:    "Prime Ministers Gold Medal" Bangladesh - For Achieving Highest CGPA among all the Departments in the University of Chittagong for the academic year 2015.
  • 2017:    ERASMUS+: Erasmus Mundus Scholarship (EMJMD) – by the European Union. European Master’s Program in Language and Communication Technologies (LCT).
  • 2014:    Awarded and Certified for securing 3rd place in "National awareness and skill-building program for mobile application development 2014" run by the Ministry of ICT Bangladesh.
  • 2013:    Awarded as "Divisional Champion" in ACM-ICPC (International Collegiate Programming Contest) Asia Regional Dhaka site 2013.



 Semantic Scholar:    link    | Google Scholar:    link   |   Scopus Author ID:    57212514987   |   ORCID iD:    link

Book Chapters:

1)     M. A. Rahman, Tabassum, N., Paul, M., Pal, R., & Islam, M. K. (2023). « BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation”. In Computer Vision and Image Analysis for Industry 4.0 (pp. 1-16). Chapman and Hall/CRC.

2)     M. A. Rahman, Y. A. Akter, “Multi-lingual Author Profiling: Predicting Gender and Age from Tweets!”, In Chen JZ., Tavares J., Shakya S., Iliyasu  A. (eds) Image   Processing and Capsule Networks. ICIPCN 2020. Advances in Intelligent Systems and Computing, vol 1200. Springer, Cham (ISBN:  978-3-030-51859-2). DOI:


3)     Y. A. Akter, M. A. Rahman, M. O. Rahman, “Quantitative Analysis of Mouza Map to Estimate Land Area using Zooming and Canny Edge Detection”, TELKOMNIKA (Telecommunication Computing Electronics and Control - ISSN 1693-6930), Vol 18, No 6: December 2020: 3293-3302. DOI:

4)     Hossain, T. B., Y. A. Akter, and M. A. Rahman. “Voice Mail Application for Visually Impaired Persons”. Recent Research in Science and Technology, Vol. 12, no. 1, Jan. 2020, pp. 15-18.

Conference Proceedings:

5)     Jubaer, S.M., Tabassum, N., Rahman, M.A., Islam, M.K. (2023). “BN-DRISHTI: Bangla Document Recognition Through Instance-Level Segmentation of Handwritten Text Images”. In: Coustaty, M., Fornés, A. (eds) Document Analysis and Recognition – ICDAR 2023 Workshops. ICDAR 2023. Lecture Notes in Computer Science, vol 14194. Springer, Cham.

6)     D. Ruiter, M. A. Rahman, D. Klakow, “LSV-UdS Participation at HASOC 2019: The Problem of Defining Hate”, In the 11th meeting of Forum for Information Retrieval Evaluation (FIRE) 2019, IRI, Kolkata, India.

7)     M. A. Rahman, Y. A. Akter, “Topic Classification from text using Decision Tree, K-NN and Multinomial Naïve Bayes”, In International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), EWU, Dhaka, Bangladesh.

8)     M. A. Rahman, M. H. Seddiqui, “Comparison of Classical Machine Learning Approaches on Bangla Textual Emotion Analysis”, 21st International Conference of Computer and Information Technology (ICCIT), 21-23 December, 2018, UIU, Dhaka, Bangladesh.

9)     Y. A. Akter, M. A. Rahman, “Extracting RDF Triples from Raw Text” In International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), EWU, Dhaka, Bangladesh.

10)  R. Sadia, M. A. Rahman, M. H. Seddiqui, “N-gram Statistical Stemmer for Bangla Corpus”, In Proceedings of 6th International Conference on Natural Sciences and Technology (ICNST’19) March 29 - 30, 2019, Asian University for Women, Chittagong, Bangladesh.

11)  M. A. Rahman, P. Chakraborty, (2021, February). “Opinion Mining: Is Feature Engineering Still Relevant?”. In 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD) (pp. 55-59). IEEE.


12)  M. A. Rahman, M. H. Seddiqui (2020), “BanglaEmotion: A Benchmark Dataset for Bangla Textual Emotion Analysis”, Mendeley Data, V1, DOI: 10.17632/24xd7w7dhp.1

13)  M. A. Rahman, Mitu Paul, Nazifa Tabassum, Riya Pal, Bipon Das, Raisa Tasnim, Osman Gony, Fatin Noor, Sheikh Mohammad Jubaer, Mehanaz Chowdhury, Yeasmin Ara Akter, Mohammad Khairul Islam - “BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR)”, Mendeley Data, V1, DOI: 10.17632/743k6dm543.1


Coauthorship graph