Piush Aggarwal

Piush Aggarwal (MSc, BTech) Photo: Henrik Schipper

Piush Aggarwal (MSc, BTech)

Research assistant at the professorship "Computational Linguistics" in the project KISTRA

Email: piush.aggarwal

Universitätsstr. 27 – PRG / Building 5
Room B 117 (1st floor)
58097 Hagen

What is my role within CATALPA?

As a computer scientist in NLP, I work on analysing robustness and explanations of multimodal systems having language as one of the modality.


In CATALPA, I can propose my research to a diverse and interdisciplinary area of expertise which would be helpful for me to provide visionary suggestions and a global perspective of the problem I am trying to solve. Multimodal solutions to NLP is need lots of expertise and visionary road maps that i am confident to get it from CATALPA.

    • From April 2022: Research assistant at professorship "Computational Linguistic" at the Research Center CATALPA („Center of Advanced Technology Assisted Learning and Predictive Analytics“) , FernUniversität in Hagen
    • 01. 2019 - 03. 2022: Researcher at Language Technology Lab, Universität Duisburg-Essen
    • 04. 2017 - 07.2019: M.Sc. in Computer Engineering with Specialization in Intelligent Networked Systems at University of Duisburg-Essen
    • 11. 2017 - 10.2018: Human Language Technology’s Assistant at eBay Inc.
    • 09. 2015 - 03.2017: Business Intelligence Engineer at Bank of America
    • 10. 2014 - 09.2015: e-Discovery Engineer at Xerox
    • 06. 2012 - 10. 2014: Business Intelligence Engineer at Standard Chartered Bank
    • 08. 2008 – 03. 2012: B.Tech. in Electronics and Communications at Guru Gobind Singh Indraprastha University, Delhi, India
    • Multimodal Solutions to NLP applications
    • Robustness of ML systems
    • Explanation AI
  • I am currently working in different projects of the professorship "Computational Linguistics".

  • 2024


    • Aggarwal, P., Mehrabanian, J., Huang, W., Alacam, Ö., & Zesch, T. (2024). Text or image? What is more important in cross-domain generalization capabilities of hate meme detection models? In Y. Graham & M. Purver (Eds.), 18th conference of the european chapter of findings of the association for computational linguistics (pp. 104–117). Association for Computational Linguistics. https://openreview.net/forum?id=RZYrUlRGv1



    • Aggarwal, P., Chawla, P., Das, M., Saha, P., Mathew, B., Zesch, T., & Mukherjee, A. (2023). HateProof: Are hateful meme detection systems really robust? Proceedings of the ACM Web Conference 2023, 3734–3743. https://doi.org/10.1145/3543507.3583356



    • Aggarwal, P., & Zesch, T. (2022a). Analyzing the real vulnerability of hate speech detection systems against targeted intentional noise. Proceedings of the Eighth Workshop on Noisy User-Generated Text (w-NUT 2022), 230–242. https://aclanthology.org/2022.wnut-1.25
    • Aggarwal, P., & Zesch, T. (2022b). Bye, bye, maintenance work? Using model cloning to approximate the behavior of legacy tools. Proceedings of the 18th Conference on Natural Language Processing (KONVENS 2022), 175–180. https://aclanthology.org/2022.konvens-1.21



    • Aggarwal, P., Liman, M. E., Gold, D., & Zesch, T. (2021). VL-BERT+: Detecting Protected Groups in Hateful Multimodal Memes. Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), 207–214. https://doi.org/10.18653/v1/2021.woah-1.22
    • Pham, D. D., Müller, J., Aggarwal, P., Khatri, A., Sharma, M., Zesch, T., & Pauli, J. (2021, January). Fully vs. Weakly Supervised Caries Localization in Smartphone Images with CNNs. Artificial Intelligence for Healthcare Applications International Workshop - ICPR 2020 Workshop Proceedings.