This image shows Annerose Eichel

Annerose Eichel

Doctoral Researcher
Institute for Natural Language Processing
Foundations of Computational Linguistics

Contact

Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Room: 01.011

Office Hours

Upon request via e-mail.

Subject

I am a Ph.D. student under the supervision of Apl. Prof. Dr. Schulte Sabine Schulte im Walde. Until June 1, 2022, I was a PhD associate with the Robert Bosch GmbH in Plochingen, Germany, in the Text and Data Mining team. Since August 1, 2022, I hold a full-time scholarship funded by the Hanns Seidel Foundation.

My work focuses on modeling plausibility in NLP. I am specifically interested in exploring cognitive and socio-linguistics aspects as well as multilinguality.

I regularly contribute as a reviewer for NLP conferences and workshops: EACL 2023, SemEval-2023, WASSA 2023, EMNLP 2023, LREC-COLING 2024, SRW NAACL 2024, ACM-WebSci24.

Since August 2023, Yarik Menchaca Resendiz and I represent the interests of all doctoral researchers at the IMS. If you have questions or would like to communicate an issue or concern, please do not hesistate to contact either of us!

Twitter | LinkedIn

Annerose Eichel and Sabine Schulte im Walde. 2024. Multi-Task Learning with Adapters for Plausibility Prediction: Bridging the Gap or Falling into the Trenches? Insights from Negative Results in NLP. Mexico City, Mexico: NAACL, June.

Annerose Eichel, Tana Deeg, Andre Blessing, Milena Belosevic, Sabine Arndt-Lappe, and Sabine Schulte im Walde. 2024. Willkommens-Merkel, Chaos-Johnson, and Tore-Klose: Modeling the Evaluative Meaning of German Personal Name Compounds. LREC-COLING 2024. Turin, Italien: ELRA, Mai.

Sabine Arndt-Lappe, Milena Belosevic, André Blessing, Tana Deeg, Annerose Eichel, and Sabine Schulte im Walde. Merci-Jens and Villen-Spahn. 2024. The evaluative semantics of personal name compounds in German. EvalMo 2024. Berlin, Germany: March. (abstract)

Annerose Eichel and Sabine Schulte im Walde. 2023. A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement. AMLAP 2023. Donostia-San Sebastian, Spain: BCBL, August. (abstract)

Annerose Eichel and Sabine Schulte im Walde. 2023. A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement. LAW-XVII 2023. Toronto, Canada: ACL, July.

Neele Falk*, Annerose Eichel*, und Prisca Piccirilli*.  2023. NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques. SemEval-2023. Toronto, Canada: ACL, July. *equal contribution

Annerose Eichel, Helena Schlipf und Sabine Schulte im Walde. 2023. Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain. EACL 2023. Dubrovnik, Croatia: EACL, May.

Annerose Eichel, Gabriella Lapesa, und Sabine Schulte im Walde. 2022. Investigating Independence vs. Control: Agenda-Setting in Russian News Coverage on Social Media. LREC 2022. Marseille, France: ELRA, June.

  • WS 23/24, SS 24 Modeling Semantic Plausibility
  • 2021-Present, PhD., Computational Linguistics, University of Stuttgart.
  • 2018-2021, MSc., Computational Linguistics, University of Stuttgart.
  • 2017-2018, Graduate Studies, International Studies of Computational Linguistics, Eberhard Karls University of Tübingen.
  • 2013-2017, BA., Language, Culture, and Translation, German-Russian-English, Johannes Gutenberg University of Mainz.

Bachelor Students:

Tana Deeg. BSc. Natural Language Processing. University of Stuttgart (with Sabine Schulte im Walde)
Modeling the evaluative nature of German personal name compounds. (2023)

Master Students:

Frederik Wagner. MSc. Computer Science. University of Stuttgart (with Sabine Schulte im Walde)
Exploring Retrieval-Augmented Language Modeling for Material Prediction of Vehicle Components. (ongoing)

Helena Schlipf. MSc. Computational Linguistics. University of Stuttgart, in collaboration with the Robert Bosch GmbH (with Sabine Schulte im Walde)
Learning domain-specific material properties in the vehicle repair information domain using unstructured and structured data sources. (2022)

To the top of the page