Anastasiia Sedova

I am a final-year PhD student in the NLP Lab at the University of Vienna, Data Mining and Machine Learning Research Group, where I am advised by Ben Roth, working on machine learning and natural language processing. Currently, I’m interning at Machine Learning Research team at Apple under supervision of Maartje Ter Hoeve and Natalie Schluter.
Previously, I completed my M.Sc. degrees in Computational Linguistics and Computer Science in the Center for Information and Language Processing at LMU Munich with a full scholarship from the German Academic Exchange Service.
My research interests include (but not limited to) model explainability and trustworthiness as well as noisy and low-resource learning.
news
Apr 07, 2025 | Extremely excited to start an internship at Machine Learning Research at Apple! I will work with Maartje Ter Hoeve and Natalie Schluter. |
---|---|
Nov 06, 2024 | Happy to be recognized as an EMNLP’24 outstanding reviewer! |
Sep 20, 2024 | Our paper To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity was accepted to EMNLP 2024 Findings! A joint work with MaiNLP lab. |
May 20, 2024 | I gave an invited tutorial at the Department of Statistics at LMU Munich. |
Feb 01, 2024 | This February I will spend in Munich for a one-month research stay at Hinrich Schütze’s Lab. |
Oct 07, 2023 | Our paper ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision was accepted to EMNLP 2023! See you in Singapore! |
Sep 28, 2023 | I am in Copenhagen to give an invited tutorial at Aalborg University. Check out the materials. |
Jun 06, 2023 | Our paper Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal was accepted to ECML PKDD 2023! |
May 27, 2023 | Our paper ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion was accepted to ACL 2023! Check out the poster. |
Jan 20, 2023 | I gave an invited talk at the Technical University of Vienna on the potential application and future perspectives of weak supervision. |