Mohammad Arvan

Ph.D. Candidate, CS Department, University of Illinois at Chicago

profile_pic.png

851 S. Morgan St.

Chicago, IL, 60607

Hey there! I’m Mohammad Arvan, a Ph.D. candidate in Computer Science at the University of Illinois at Chicago, under the supervision of Dr. Natalie Parde. My research is centered on improving the reliability of machine learning, with a particular focus on evaluation and reproducibility. I advocate for Open Science, emphasizing transparency, equity, and inclusivity in research practices. With a strong engineering background, I prioritize practical solutions to enhance the trustworthiness of machine learning technologies.

news

Jun 12, 2022 ‘Reproducibility of Exploring Neural Text Simplification Models: A Review’ was accepted at 15th International Natural Language Generation Conference
Jan 2, 2021 Ranked top 8% on Stackoverflow’s 2020 year rank
Dec 8, 2020 Proud recipient of PGRA award ($5000)

latest posts

Nov 17, 2022 Reproducibility: on why and how

selected publications

  1. Reproducibility in Computational Linguistics: Is Source Code Enough?
    Mohammad Arvan, Luı́s Pina, and Natalie Parde
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, 2022
  2. Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
    Anya Belz, Craig Thomson, Ehud Reiter, and 36 more authors
    In The Fourth Workshop on Insights from Negative Results in NLP, May 2023