about

I am a fourth year phd candidate at the lab of machine learning at Humboldt University of Berlin, supervised by Prof. Dr. Alan Akbik. My research focuses on data-efficient transfer learning, mainly around structured information extraction.

news

[25 | 03] - Paper accepted @ ICLR'25: Our paper MastermindEval: A Simple But Scalable Reasoning Benchmark got accepted to ICLR 2025 Workshop on Reasoning and Planing for LLMs!
[24 | 12] - Paper accepted @ NAACL'25: Our paper Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training Data got accepted to NAACL 2025!
[24 | 10] - Paper accepted @ CoNLL'24: Our paper BabyHGRN: Exploring RNNs for Sample-Efficient Language Modeling got accepted to CoNLL 2024 as part of the BabyLM Challenge.
[24 | 10] - Teaching (winter term 24/25): We give a seminar on efficient machine learning for natural language processing this semester (winter 24/25).
[24 | 06] - Summer internship @ Amazon: I will be doing a 14-week summer internship at Amazon Alexa AI in Santa Barbara!
[24 | 03] - PECC available on Hugging Face: Our PECC dataset and the corresponding leaderboard is available on Hugging Face!
[24 | 02] - Paper accepted @ COLING'24: Our paper PECC: Problem Extraction and Coding Challenges got accepted to LREC-COLING 2024!
[24 | 01] - Paper accepted @ EACL'24: Our paper Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition got accepted to EACL 2024!
[23 | 10] - Paper accepted @ EMNLP'23: Our paper Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs got accepted to EMNLP 2023!
[23 | 06] - New open-source package: Our open-source package for generating synthetic datasets, fabricator, is available on GitHub.
[22 | 11] - BLOOM paper on arxiv: Our paper BLOOM: A 176B-Parameter Open-Access Multilingual Language Model is now available on arXiv!
[22 | 09] - Paper accepted @ NeurIPS'22: Our paper BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing got accepted to NeurIPS 2022!
[06 | 22] - BigBio paper on arxiv: Our paper on BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing is now available on arxiv! Check also the entire BigScience workshop for more cool stuff.