Maximilian Müller-Eberstein

Publikation

Publikationer pr. år 2021 2022 2023 2024 2024

• 14 Konferencebidrag i proceedings
• 1 Ph.d.-afhandling
• 1 Paper
• 1 Tidsskriftartikel

Publikationer pr. år

Publikationer pr. år

Søgeresultater

• 2024

  Can Humans Identify Domains?

  Barrett, M. J., Müller-Eberstein, M., Bassignana, E., Pauli, A. B., Zhang, M. & van der Goot, R., 2024, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). European Language Resources Association

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Natural Language Processing 100%
  • Prose 100%
  • Dewey 100%
  • Genre 100%
  • Annotation 100%

• Enough Is Enough! a Case Study on the Effect of Data Size for Evaluation Using Universal Dependencies

  van der Goot, R., Liu, Z. & Müller-Eberstein, M., 1 maj 2024, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S. & Xue, N. (red.). Torino, Italia: ELRA and ICCL, s. 6167-6176 10 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang
• 2023

  DanTok: Domain Beats Language for Danish Social Media POS Tagging

  Hansen, K. K., Barrett, M. J., Müller-Eberstein, M., Damgaard, C., Eriksen, T. & van der Goot, R., 2023, Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa). s. 271–279 9 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Annotation 100%
  • Specialised Domain 50%
  • Source Modeling 50%
  • Switching Uncertainties 50%
  • Human Uncertainty 50%

• Establishing Trustworthiness: Rethinking Tasks and Model Evaluation

  Litschko, R., Müller-Eberstein, M., van der Goot, R., Weber-Genzel, L. & Plank, B., 6 dec. 2023, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics, s. 193-203 10 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Trustworthiness 100%
  • Natural Language Processing 100%
  • Evaluation Model 100%
  • Evaluation Protocol 100%
  • Large Language Models 100%

• On Language Spaces, Scales and Cross-Lingual Transfer of UD Parsers

  Samardžić, T., Gutierrez-Vasques, X., van der Goot, R., Müller-Eberstein, M., Pelloni, O. & Plank, B., dec. 2023, Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL). Association for Computational Linguistics, Bind 26. s. 266-281 16 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Parser 100%
  • Language Space 100%
  • Syntactics 100%
  • Parsing 100%
  • Related Language 100%

• Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training

  Müller-Eberstein, M., van der Goot, R., Plank, B. & Titov, I., 6 dec. 2023, Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: Association for Computational Linguistics, s. 13190-13208

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Training Model 100%
  • Information Sharing 100%
  • Language Model 100%
  • Linguistic Information 100%
  • Share Information 100%
• 2022

  Evidence > Intuition: Transferability Estimation for Encoder Selection

  Bassignana, E., Müller-Eberstein, M., Zhang, M. & Plank, B., 7 dec. 2022, The 2022 Conference on Empirical Methods in Natural Language Processing: EMNLP 2022. Abu Dhabi, United Arab Emirates: Association for Computational Linguistics, s. 4218–4227

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Encoder 100%
  • Language Model 100%
  • Language Modeling 100%
  • Natural Language Processing 60%
  • Computer Vision 20%

• Experimental Standards for Deep Learning in Natural Language Processing Research

  Ulmer, D. T., Bassignana, E., Müller-Eberstein, M., Varab, D., Zhang, M., van der Goot, R., Hardmeier, C. & Plank, B., 7 dec. 2022, Findings of 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). 20 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Natural Language Processing 100%
  • Deep Learning 100%
  • Deep Learning Method 100%
  • Explosive Growth 33%
  • Public Repositories 33%

• Frustratingly Easy Performance Improvements for Low-resource Setups: A Tale on BERT and Segment Embeddings

  van der Goot, R., Müller-Eberstein, M. & Plank, B., 2022, Proceedings of the Language Resources and Evaluation Conference. s. 1418-1427

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Performance Improvement 100%
  • Low-resource 100%
  • Segment Embeddings 100%
  • BERT Embeddings 100%
  • Bidirectional Encoder Representations From Transformers 100%

• Probing for Labeled Dependency Trees

  Müller-Eberstein, M., van der Goot, R. & Plank, B., 2022, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, s. 7711-7726

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Natural Language Processing 100%
  • Linear Probe 100%
  • Parser 100%
  • Dependency Tree 100%
  • dependency parse 100%

• Sort by Structure: Language Model Ranking as Dependency Probing

  Müller-Eberstein, M., van der Goot, R. & Plank, B., 2022, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, s. 1296-1307

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Language Model 100%
  • Model Ranking 100%
  • Language Modeling 100%
  • Parser 50%
  • Order of Magnitude 25%

• Spectral Probing

  Müller-Eberstein, M., van der Goot, R. & Plank, B., dec. 2022, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, United Arab Emirates: Association for Computational Linguistics, s. 7730-7741

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Spectral Profile 100%
  • Subword 50%
  • Contextual Embeddings 50%
  • Frequency Filtering 50%
  • Granular Analysis 50%
• 2021

  Genre as Weak Supervision for Cross-lingual Dependency Parsing

  Müller-Eberstein, M., van der Goot, R. & Plank, B., nov. 2021, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Online and Punta Cana, Dominican Republic: Association for Computational Linguistics, s. 4786-4802

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Cross-lingual 100%
  • Dependency Parsing 100%
  • Unsupervised Learning 100%
  • Data Selection 100%
  • dependency parse 100%

• How Universal is Genre in Universal Dependencies?

  Müller-Eberstein, M., van der Goot, R. & Plank, B., dec. 2021, Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021). Sofia, Bulgaria: Association for Computational Linguistics, s. 69-85

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Universal Dependencies 100%
  • Instance Level 100%
  • Treebank 80%
  • Annotation 50%
  • Varying Degree 50%