Tsegaye Misikir Tashu

Tsegaye Misikir Tashu, Ph.D.

Lecturer

I am a researcher and educator with extensive experience in teaching, mentoring, and conducting interdisciplinary research in Natural Language Processing (NLP) and Machine Learning. My work focuses on developing human-centred models and applications across four key domains: NLP for Education, Emotion Recognition, Multilingual Representation Learning, and Efficient and Scalable Large Language Models (LLMs).

I am determined to guide the next generation of applied researchers. My goal is to facilitate an environment of collaboration and innovation, supporting students in developing original, high-quality research and practical solutions that advance both theory and real-world applications. Currently, I serve as a lecturer at Breda University of Applied Sciences and an Assistant Professor at the University of Groningen’s Bernoulli Institute, where I specialize in NLP and Machine Learning.

Expertise

  • Natural Language Processing (NLP)
  • Machine Learning
  • Deep Learning
  • Large Language Models (LLM)

Teaching

  • Natural Language Processing (NLP)
  • Machine Learning

Education

  • PhD in Computer Science (Specilization in Natural Language Processing), Eötvös Loránd University, 2021
  • Masters in Informations Science, Addis Ababa University, 2014
  • Bachelors in Informations Science, Addis Ababa University, 2011

Publications

2025

  1. Angelov, A., Tashu, T. M., & Valdenegro-Toro, M. Difficulty Estimation in Natural Language Tasks with Action Scores In Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025), pp. 351–364.
  2. Tashu, T. M., Kontos, E. R., Sabatelli, M., & Valdenegro-Toro, M. Cross-Lingual Document Recommendations with Transformer-Based Representations: Evaluating Multilingual Models and Mapping Techniques In Proceedings of the Second Workshop on Scaling Up Multilingual & Multi-Cultural Evaluation, pp. 39–47.
  3. Tashu, T. M., & Tudor, A. I. Mapping Cross-Lingual Sentence Representations for Low-Resource Language Pairs Using Pre-trained Language Models In Proceedings of the First Workshop on Language Models for Low-Resource Languages, pp. 249–257.

2024

  1. Philip, H., & Tashu, T. M. Phrase-Level Adversarial Training for Mitigating Bias in Neural Network-based Automatic Essay Scoring arXiv preprint arXiv:2409.04795.
  2. Mahajan, V., Birihanu, E., & Tashu, T. M. A Dynamic Session-Based Recommendation System with Graph Neural Networks *Proceedings of ITAT’24: Information Technologies – Applications and Theory, *, 2024.

2023

  1. Fergan, E., & Tashu, T. M. Course Review Sentiment Analysis: A Comparative Study Of Machine Learning and Deep Learning Methods In Proceedings of the 10th International Conference on Behavioural and Social Computing (BESC 2023), pp. 1–7. IEEE.
  2. Tashu, T. M., Lenz, M., & Horváth, T. NCC: Neural Concept Compression for Multilingual Document Recommendation Applied Soft Computing, 142, 110348. Elsevier.