Mareike Hartmann

Hi, I am Mareike, a PostDoc at the Computational Linguistics Group of the Department of Language Science and Technology at Saarland University.

My current research interests are LLM-based agents interacting with external environments and augmented LLMs.

Before joining UdS, I worked as a researcher at the Department for Interactive Machine Learning at DFKI, and obtained a PhD from the University of Copenhagen.

Publications

2024

Harsh Trivedi, Tushar Khot, Mareike Hartmann, Ruskin Manku, Vinty Dong, Edward Li, Shashank Gupta, Ashish Sabharwal, and Niranjan Balasubramanian
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
Best resource paper
Daniil Gurgurov, Mareike Hartmann, and Simon Ostermann
Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters
Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024).
Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, and Tushar Khot
ADaPT: As-Needed Decomposition and Planning with Language Models
Findings of the Association for Computational Linguistics: NAACL 2024.

2023

Siting Liang, Mareike Hartmann, and Daniel Sonntag
Cross-domain German Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types
Proceedings of the 5th Clinical Natural Language Processing Workshop.
Aliki Anagnostopoulou, Mareike Hartmann, and Daniel Sonntag
Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory
Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP).
Rasmus Jørgensen, Oliver Brandt, Mareike Hartmann, Xiang Dai, Christian Igel, and Desmond Elliott
MultiFin: A Dataset for Multilingual Financial NLP
Findings of the Association for Computational Linguistics: EACL 2023.

2022

Mareike Hartmann, Han Du, Nils Feldhus, Ivana Kruijff-Korbayová, and Daniel Sonntag
XAINES: Explaining AI with narratives
KI-Künstliche Intelligenz.
Mareike Hartmann and Daniel Sonntag
A survey on improving NLP models with human explanations
Proceedings of the First Workshop on Learning with Natural Language Supervision.

2021

Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai, and Desmond Elliott
mDAPT: Multilingual Domain Adaptive Pretraining in a Single Model
Findings of the Association for Computational Linguistics: EMNLP 2021.
Nicolas Garneau, Mareike Hartmann, Anders Sandholm, Sebastian Ruder, Ivan Vulić, and Anders Søgaard
Analogy Training Multilingual Encoders
Proceedings of the AAAI Conference on Artificial Intelligence.
Mareike Hartmann and Anders Søgaard
Multilingual Negation Scope Resolution for Clinical Text
Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis.
Mareike Hartmann, Miryam de Lhoneux, Daniel Hershcovich, Yova Kementchedjhieva, Lukas Nielsen, Chen Qiu, and Anders Søgaard
A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs
Proceedings of the 25th Conference on Computational Natural Language Learning.

2019

Mareike Hartmann, Yevgeniy Golovchenko, and Isabelle Augenstein
Mapping (Dis-)Information Flow about the MH17 Plane Crash
Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda.
Yova Kementchedjhieva, Mareike Hartmann, and Anders Søgaard
Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
Mareike Hartmann, Tallulah Jansen, Isabelle Augenstein, and Anders Søgaard
Issue Framing in Online Discussion Fora
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers).
Mareike Hartmann, Yova Kementchedjhieva, and Anders Sø gaard
Comparing Unsupervised Word Translation Methods Step by Step
Advances in Neural Information Processing Systems.

2018

Yevgeniy Golovchenko, Mareike Hartmann, and Rebecca Adler-Nissen
State, media and civil society in the information warfare over Ukraine: citizen curators of digital disinformation
International affairs.
Mareike Hartmann, Yova Kementchedjhieva, and Anders Søgaard
Why is unsupervised alignment of English embeddings from different algorithms so hard?
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
Bolette Pedersen, Sanni Nimb, Anders Søgaard, Mareike Hartmann, and Sussi Olsen
A Danish FrameNet Lexicon and an Annotated Corpus Used for Training and Evaluating a Semantic Frame Classifier
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
Mareike Hartmann and Anders Søgaard
Limitations of Cross-Lingual Learning from Image Search
Proceedings of the Third Workshop on Representation Learning for NLP.

Teaching

At Saarland University


SS 2024

  • Semantic Theory

  • WS 2023/2024

  • Foundations of Linguistics (Semantics)
  • Seminar: NLP for Low-Resource Languages
  • Guest lecture: NLP for low-resource settings

  • SS 2023

  • Semantic Theory

  • WS 2022/2023

  • Foundations of Linguistics (Semantics)
  • Seminar: Cross-Lingual Learning
  • Seminar: Learning from Explanations