Elamur Research⌕
☰
home / papers / 2026 / AmDi - Ambiguous Words Diachronic Dataset

AmDi - Ambiguous Words Diachronic Dataset

Summary

German NLP has lacked a resource that serves both Word Sense Disambiguation (WSD) and Lexical Semantic Change Detection (LSCD). Sense-annotated German corpora such as TüBa-D/Z or GLASS are essentially synchronic. Diachronic sets such as SemEval-2020 Task 1 or DWUG DE do not tie usages to a fixed sense inventory. Thielen and Kugler address this with AmDi, a collection of German sentences containing ambiguous nouns. The sentences come from the DWDS corpora and are organised by decade from 1901 to 2018, with blog and Wikipedia material added for recent years. Student annotators labelled each usage with a GermaNet synset, and only instances with complete annotator agreement were retained. Rare senses were reinforced with sentences containing synonymous or compound words. The authors also provide baselines: fine-tuned transformer classifiers, few-shot LLM prompting enriched with GermaNet sense information, unsupervised usage clustering, and static and contextual embeddings for measuring drift. The supplied excerpt does not include the numerical baseline results. Because every sense is both time-stamped and linked to a lexicon, AmDi enables interpretable, sense-level evaluation of semantic change.

Key points

  • Size: 22,230 samples, 637,871 tokens, 26 lexemes, 80 GermaNet senses and 14 timespans. Subsets "small" (21,363 samples, 69 synsets) and "tiny" (17,810 samples, 46 synsets) merge rare classes into "None" using a mean-minus-k·σ threshold.
  • Sources: the DWDS corpora public (1901–2018, the main source), blogs (1995–2014) and wikipedia (2006–2023), retrieved through the DWDS JSON API.
  • Annotation:
    • 17 mostly high-frequency polysemous base nouns (e.g., Bank, Schimmel, Tor, Maske, Virus) were annotated by 16 native-speaker students. The first round of 10,020 instances reached 79% agreement.
    • 57 synonymous words were then added to cover rarer senses.
    • Keeping only fully agreed samples discarded about 3% of the data (750 of 22,980).
  • WSD baselines:
    • Fine-tuning of gBERT-large, XLM-RoBERTa-large and XL-LEXEME on a stratified 90/10 split.
    • Few-shot prompting of six models.
    • Unsupervised clustering of usages.
  • LSCD baselines: static word vectors trained on time-segmented corpus slices, and contextual embeddings from pretrained and fine-tuned models, with per-lexeme cosine and Jaccard drift analyses.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Word sense disambiguation

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/46xmhmibv9hz

@inproceedings{thielen2026amdi,
  title = {{AmDi - Ambiguous Words Diachronic Dataset}},
  author = {Thielen, Felix and Kugler, Kai},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/46xmhmibv9hz},
  url = {https://doi.org/10.63317/46xmhmibv9hz}
}

References

56 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mohamad Ballout, Anne Dedert, Nohayr Muhammad Abdelmoneim, Ulf Krumnack, Gunther Heidemann, and Kai-Uwe Kühnberger. 2024. FOOL ME IF YOU CAN! an adversarial dataset to investigate the robustness of LMs in word sense disambiguation. In Proceedings of the 2024 Conference on Empirical Methods in Natura… find
  2. Pierpaolo Basile, Lucia Siciliani, Elio Musacchio, and Giovanni Semeraro. 2025. Exploring the word sense disambiguation capabilities of large language models. find
  3. Michele Bevilacqua and Roberto Navigli. 2020. Breaking through the 80% glass ceiling: Raising the state of the art in word sense disambiguation by incorporating knowledge graph information. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2854–2864, O… find
  4. Michele Bevilacqua, Tommaso Pasini, Alessandro Raganato, and Roberto Navigli. 2021. Recent trends in word sense disambiguation: A survey. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 4330–4338. International Joint Conferences on Artificia… find
  5. Anna Breit, Artem Revenko, Kiamehr Rezaee, Mohammad Taher Pilehvar, and Jose Camacho-Collados. 2021. WiC-TSV: An evaluation benchmark for target sense verification of words in context. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Mai… find
  6. Samuel Broscheit, Anette Frank, Dominic Jehle, Simone Paolo Ponzetto, Danny Rehl, Anja Summa, Klaus Suttner, and Saskia Vola. 2010. Rapid bootstrapping of word sense disambiguation resources for german. In Semantic Approaches in Natural Language Processing : Proceedings of the Conference on Natural… find
  7. Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. 2013. API design for machine learning software: experie… find
  8. Ricardo JG Campello, Daniel Moulavi, and Jörg Sander. 2013. Density-based clustering based on hierarchical density estimates. In Advances in Knowledge Discovery and Data Mining, pages 160–172. Springer. find
  9. Pierluigi Cassotti, Lucia Siciliani, Marco DeGemmis, Giovanni Semeraro, and Pierpaolo Basile. 2023. XL-LEXEME: WiC pretrained model for cross-lingual LEXical sEMantic changE. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 15… find
  10. Branden Chan, Stefan Schweter, and Timo Möller. 2020. German’s next language model. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, pages 6788–6796. International Committee on Computational Linguistics. find our card
  11. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association fo… find
  12. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, and Qihao Zhu et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. find our card
  13. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  14. Philip Edmonds and Scott Cotton. 2001. Senseval-2: Second international workshop on evaluating word sense disambiguation systems. In Proceedings of Senseval-2. find
  15. Tony Finch. 2009. Incremental calculation of weighted mean and variance. find
  16. Mario Giulianelli, Marco Del Tredici, and Raquel Fernández. 2020. Analysing lexical semantic change with contextualised word representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3960–3973, Online. Association for Computational Linguistics… find our card
  17. Dirk Goldhahn, Thomas Eckart, and Uwe Quasthoff. 2012. Building large monolingual dictionaries at the Leipzig corpora collection: From 100 to 200 languages. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 759–765, Istanbul, Turkey. European… find our card
  18. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, and Akhil Mathur et al. 2024. The llama 3 herd of models. find
  19. William L. Hamilton, Jure Leskovec, and Dan Jurafsky. 2016. Diachronic word embeddings reveal statistical laws of semantic change. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1489–1501, Berlin, Germany. Association for Com… find our card
  20. Birgit Hamp and Helmut Feldweg. 1997. GermaNet - a lexical-semantic net for German. In Automatic Information Extraction and Building of Lexical Semantic Resources for NLP Applications. find our card
  21. Erhard Henrich, Verena; Hinrichs. 2014. Consistency of manual sense annotation and integration into tüba-d/z treebank. Proceedings of the Thir-teenthInternational Workshop on Treebanksand Linguistic Theories (TLT13) : December 12-13, 2014, Tübingen, Germany / Editors: Verena Henrich, Erhard Hinrichs… find
  22. Verena Henrich. 2015. Word Sense Disambiguation with GermaNet. Ph.D. thesis, University of Tübingen, Germany. find
  23. Franziska Horn. 2021. Exploring word usage change with continuously evolving embeddings. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 290–297, Online… find
  24. Lawrence Hubert and Phipps Arabie. 1985. Comparing partitions. Journal of Classification, 2(1):193–218. find
  25. Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, and Alexandre Ramé et al. 2025. Gemma 3 technical report. find
  26. L. Kaufman and P. J. Rousseeuw. 1990. Finding Groups in Data: An Introduction to Cluster Analysis. Wiley. find
  27. Harold W. Kuhn. 1955. The hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83–97. find
  28. James MacQueen. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, volume 1, pages 281–297. find
  29. Matej Martinc, Petra Kralj Novak, and Senja Pollak. 2020. Leveraging contextual embeddings for detecting diachronic semantic shift. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4811–4819, Marseille, France. European Language Resources Association. find
  30. Leland McInnes, John Healy, and James Melville. 2018. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426. find our card
  31. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS’13, page 3111–3119, Red Hook, NY,… find
  32. Tristan Miller, Mohamed Khemakhem, Richard Eckart de Castilho, and Iryna Gurevych. 2016. Sense-annotating a lexical substitution data set with ubyline. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 828–835, Portorož, Slovenia. European Lan… find
  33. Mistral AI Team. 2025. Mistral Small 3.1: A New Leader in the Small Models Category with Image Understanding Capabilities. https://mistral.ai/news/mistral-small-3-1. Blog post released March 17, 2025. ↗
  34. Andrea Moro and Roberto Navigli. 2015. SemEval-2015 task 13: Multilingual all-words sense disambiguation and entity linking. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 288–297, Denver, Colorado. Association for Computational Linguistics. find
  35. Ollama Team. 2025. Ollama. GitHub Repository. Version 0.11.3. find
  36. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics. find
  37. Radim Rehurek and Petr Sojka. 2011. Gensim– python framework for vector space modelling. NLP Centre, Faculty of Informatics, Masaryk University, Brno, Czech Republic, 3(2). find
  38. Dominik Schlechtweg. 2023. Human and computational measurement of lexical semantic change. PhD thesis. University of Stuttgart. find
  39. Dominik Schlechtweg, Barbara McGillivray, Simon Hengchen, Haim Dubossarsky, and Nina Tahmasebi. 2020. SemEval-2020 task 1: Unsupervised lexical semantic change detection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1–23, Barcelona (online). International Committee for Com… find our card
  40. Dominik Schlechtweg, Sabine Schulte im Walde, and Stefanie Eckmann. 2018. Diachronic usage relatedness (DURel): A framework for the annotation of lexical semantic change. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… find our card
  41. Dominik Schlechtweg, Nina Tahmasebi, Simon Hengchen, Haim Dubossarsky, and Barbara McGillivray. 2021. DWUG: A large resource of diachronic word usage graphs in four languages. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7079–7091, Online and Punta… find
  42. Dominik Schlechtweg, Shafqat Mumtaz Virk, and Nikolay Arefyev. 2024. The lscd benchmark: a testbed for diachronic word meaning tasks. find our card
  43. Benjamin Snyder and Martha Palmer. 2004. Senseval-3: Third international workshop on the evaluation of systems for the semantic analysis of text. In Proceedings of Senseval-3. find
  44. Alexander Strehl and Joydeep Ghosh. 2002. Cluster ensembles—a knowledge reuse framework for combining multiple partitions. Journal of Machine Learning Research, 3:583–617. find
  45. Nina Tahmasebi, Lars Borin, Adam Jatowt, Yang Xu, and Simon Hengchen, editors. 2021. Computational approaches to semantic change. Number 6 in Language Variation. Language Science Press, Berlin. find
  46. Nina Tahmasebi and Thomas Risse. 2017. Finding individual word sense changes and their delay in appearance. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 741– 749, Varna, Bulgaria. INCOMA Ltd. find
  47. Xiaohang Tang, Yi Zhou, Taichi Aida, Procheta Sen, and Danushka Bollegala. 2023. Can word sense distribution detect semantic changes of words? In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3575–3590, Singapore. Association for Computational Linguistics. find
  48. Sean Trott and Benjamin Bergen. 2021. Raw-c: Relatedness of ambiguous words–in context (a new lexical resource for english). find
  49. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research, 9:2579–2605. find
  50. Ming Wang and Yinglin Wang. 2020. A synset relation-enhanced framework with a try-again mechanism for word sense disambiguation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6229–6240, Online. Association for Computational Linguistics. find
  51. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoe… find our card
  52. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, and Chang Gao et al. 2025. Qwen3 technical report. find our card
  53. Guobiao Zhang, Wenpeng Lu, Xueping Peng, Shoujin Wang, Baoshuo Kan, and Rui Yu. 2022. find
  54. Word sense disambiguation with knowledge-enhanced and local self-attention-based extractive sense comprehension. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4061–4070, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. 11. L… find
  55. Hamp, Birgit and Feldweg, Helmut. 1997. GermaNet. Version 19.0, Universität Tübingen. find
  56. Felix Thielen and Kai Kugler. AmDi-Dataset. Computerlinguistik, Universität Trier. Version ’epsilon’. TüBa-D/Z. TüBa-D/Z – Tübinger Baumbank des Deutschen / Zeitungskorpus. Seminar für Sprachwissenschaft, University of Tübingen, 11.0. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/thielen-2026-amdi-ambiguous-words-diachronic-dataset/