About
I am a fourth-year PhD student in the NLP Lab, a part of Data Mining and Machine Learning Research Group at the University of Vienna, where I am advised by Ben Roth, working on machine learning and natural language processing. 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) data-centric methods for language models and model explainability and trustworthiness.
News
November 2024: I am at EMNLP 2024 in Miami, presenting our “To Know or Not to Know?” paper (Thursday, 10:30-12:00). Come and say hi if you are around!
October 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.
July 2024: I am at ICML’24. Ping me to grab a coffee!
June 2024: New preprints:
- Exploring prompts to elicit memorization in masked language model-based named entity recognition
- Analysing zero-shot temporal relation extraction on clinical notes using temporal consistency - accepted to BioNLP Workshop hosted at ACL 2024.
May 2024: I am at ICLR’24 serving as a volunteer. Let’s catch up!
April 2024: I gave an invited tutorial at the Department of Statistics at LMU Munich.
February 2024: I am in Munich for a one-month research stay at Hinrich Schütze’s Lab.
December 2023: I am at EMNLP 2023 in Singapore to present our ULF paper.
October 2023 : Our paper ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision was accepted to EMNLP 2023!
September 2023 : I am in Copenhagen to give an invited tutorial at Aalborg University. Check out the materials.
September 2023: I am at ECML PKDD 2023 in Turin to give an oral presentation of our paper AGRA paper (+ poster).
June 2023: Our paper Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal was accepted to ECML PKDD 2023!
May 2023: Our paper ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion was accepted to ACL 2023! Check out the poster.
January 2023: I gave an invited talk at the Technical University of Vienna on the potential application and future perspectives of weak supervision.
January 2022: I attended the ALPS2022 winter school on natural language processing organized by the University of Grenoble Alpes and Naver Labs Europe.
November 2021: I am at the 3d Workshop of European Language Resource Coordination (ELRC) to give a talk about Knodle framework.
August 2021: I am at ACL 2021 to give an oral presentation of our Knodle paper.
August 2021: I attend the OxML’21 summer school organized by AI for Global Goals in partnership with CIFAR and the University of Oxford. The program included talks by Yoshua Bengio, Sebastian Ruder, Michael Bronstein and others. Acceptance rate: ~5%.
July 2021: This summer I am taking part in Google Summer of Code. I will join DeepPavlov team to work on relation extraction in their end-to-end chatbot. Upd: check out my Medium post!
July 2021: I gave an invited talk at Munich NLP Meetup introducing our freshly-baked Knodle!
June 2021: Our paper Knodle: Modular Weakly Supervised Learning with PyTorch was accepted to the Workshop on Representation Learning for NLP (RepL4NLP) hosted at ACL 2021! (poster) Check it out here.
May 2021: I gave an invited talk at the Bosch NLP and Semantic Reasoning Lab presenting Knodle.
April 2021: Knodle first release!! Check out the source code.
I am also honored to serve as a reviewer for multiple journals and international conferences, such as ACL, EMNLP, NAACL, EACL, ECML, ILCR, IEEE PAMI, and others.
Selected Publications
- To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity
Anastasiia Sedova, Robert Litschko, Diego Frassinelli, Benjamin Roth, Barbara Plank
EMNLP 2024 Findings - ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision
Anastasiia Sedova, Benjamin Roth
EMNLP 2023 - Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal
Anastasiia Sedova, Lena Zellinger, Benjamin Roth
ECML PKDD 2023 - ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion
Anastasiia Sedova, Benjamin Roth
ACL 2023 - Knodle: Modular Weakly Supervised Learning with PyTorch
Anastasiia Sedova, Andreas Stephan, Marina Speranskaya, Benjamin Roth
RepL4NLP-2021 @ACL 2021
Thesis supervision
- Benedikt Köhler (11/2022-) Political Leaning Prediction of News Paper Articles, MSc thesis.
- Sarah Sulollari (10/2022- ) - Analysing political developments by predicting party affiliation from Austrian parliament speeches, MSc thesis.
- Lena Zellinger (01/2022-08/2022) - Gradient Matching for Learning with Noisy Data, MSc thesis (cum laude, top-3 students in 2022).