Elamur Research⌕
☰
home / papers / 2026 / GePaDeSE: A New Resource for Clause-Level Aspect in German Parliamentary Debates

GePaDeSE: A New Resource for Clause-Level Aspect in German Parliamentary Debates

Summary

Clause-level aspect resources exist mostly for English, and very few cover political language. The authors address this gap for German with GePaDeSE, a corpus of 250 Bundestag speeches (192 speakers, about 222k tokens). It is labeled with Situation Entity (SE) types following Smith (2003), such as State, Event, Generic, Generalizing, Fact and Proposition.

Two trained linguistics students labeled every finite verb directly instead of automatically segmented clauses. They followed the German SE guidelines, which add an Event-Perfect-State class for ambiguous German perfect clauses. Agreement was moderate (Cohen's κ 0.538), comparable to earlier German SE work, and most conflicts came from the State/Generic distinction.

The authors also fine-tune GBERT, EuroBERT, Llama 3.2 and LLäMmlein for multi-label SE classification, scored with micro F1, Jaccard and MASI. They then use SE types to study political discourse. The classification scores were in a section missing from the supplied text, so none are reported here.

The resource supports research on generic statements linked to stereotyping. It also supports work on epistemological bias, using the Fact vs. Proposition labels.

Key points

  • Corpus: GePaDeSE has 250 speeches, mostly from the 19th legislative term (2017–2021). It covers 192 speakers from 6 parties plus non-attached members and contains 222,387 tokens. Data, datasheet and guidelines are at github.com/umanlp/gepadese.
  • Annotation setup:
    • Finite verbs were pre-marked with dummy labels using spaCy's de_core_news_sm.
    • Annotators then corrected these labels in INCEpTION.
    • A new class, Event-Perfect-State, covers German perfect clauses that can be read as either State or Event.
  • Agreement:
    • The corpus has 19,676 SE instances.
    • Cohen's κ is 0.538, with 73% raw agreement.
    • Annotators disagreed on 5,355 cases (27%), and 39% of these involved State vs. Generic.
  • Label distribution: State is by far the most frequent type (12,321 instances), followed by Generic (2,360).
  • Modeling:
    • Four models were tested: GBERT (337M), EuroBERT (610M), Llama 3.2 1B and LLäMmlein 1B.
    • The decoder models were tuned via QLoRA (r=16, α=8, dropout 0.05, 4-bit NF4).
    • Evaluation used micro F1, Jaccard and MASI, which treat aggregated gold labels from both annotators as a set.
    • The analysis part tracks parties' self-affirmation vs. critique of others across six legislative periods.

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5jshypsv6t3k

@inproceedings{schlenker2026gepadese,
  title = {{GePaDeSE: A New Resource for Clause-Level Aspect in German Parliamentary Debates}},
  author = {Schlenker, Julian and Rehbein, Ines and Brauner, Lilly and Ertz, Florian and Reinig, Ines and Ponzetto, Simone Paolo},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5jshypsv6t3k},
  url = {https://doi.org/10.63317/5jshypsv6t3k}
}

References

69 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Malihe Alikhani and Matthew Stone. 2019. “caption” as a coherence relation: Evidence and implications. In Proceedings of the Second Workshop on Shortcomings in Vision and Language, pages 58–67, Minneapolis, Minnesota. Association for Computational Linguistics. ↗ our card
  2. Nicholas Asher. 1993. Reference to Abstract Objects in Discourse. Kluwer. ↗
  3. Maria Becker, Alexis Palmer, and Anette Frank. 2016. Argumentative texts and clause types. In Proceedings of the Third Workshop on Argument Mining (ArgMining2016), pages 21–30, Berlin, Germany. Association for Computational Linguistics. find
  4. Maria Becker, Michael Staniek, Vivi Nastase, Alexis Palmer, and Anette Frank. 2017. Classifying semantic clause types: Modeling context and genre characteristics with recurrent neural networks and attention. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 230–240, Vancouver, Canada. Association for Computational Linguistics. find
  5. Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves, André Martins, Ayoub Hammal, Caio Corro, Céline Hudelot, Emmanuel Malherbe, Etienne Malaboeuf, Fanny Jourdan, Gabriel Hautreux, João Alves, Kevin El-Haddad, Manuel Faysse, Maxime Peyrard, Nuno M. Guerreiro, Patrick Fernandes, Ricardo Rei, and Pierre Colombo. 2025. Eurobert: Scaling multilingual encoders for european languages. ↗
  6. Anne Bosse. 2024. Stereotyping and generics. Inquiry: An Interdisciplinary Journal of Philosophy, 67(10):3876–3892. find
  7. Peter F. Brown, Peter V. Desouza, Robert L. Mercer, Vincent J. Della Pietra, and Jenifer C. Lai. 1992. Class-based n-gram models of natural language. Computational linguistics, 18(4):467–479. find
  8. Martin Juan José Bucher and Marco Martini. 2024. Fine-tuned ’small’ llms (still) significantly outperform zero-shot generative ai models in text classification. ↗
  9. Federico Cabitza, Andrea Campagner, and Valerio Basile. 2023. Toward a perspectivist turn in ground truthing for predictive computing. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6):6860–6868. find our card
  10. Branden Chan, Stefan Schweter, and Timo Möller. 2020. German’s next language model. find our card
  11. Zeyu Dai and Ruihong Huang. 2018. Building context-aware clause representations for situation entity type classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3305– 3315, Brussels, Belgium. Association for Computational Linguistics. find
  12. Ilse Depraetere. 1995. On the necessity of distinguishing between (un)boundedness and (a)telicity. Linguistics and Philosophy, 18(1):1– 19. ↗
  13. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. find
  14. 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, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. ↗
  15. David R. Dowty. 1979. Word meaning and Montague grammar: the semantics of verbs and times in generative semantics and in Montague’s PTQ. Number v. 7 in Synthese language library. D. Reidel Pub. Co, Dordrecht ; Boston. find
  16. Markus Egg, Helena Prepens, and Will Roberts. 2019. Annotation and automatic classification of aspectual categories. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3335–3341, Florence, Italy. Association for Computational Linguistics. find
  17. W. Nelson Francis and Henry Kučera. 1979. Brown corpus manual. find
  18. Annemarie Friedrich and Damyana Gateva. 2017. Classification of telicity using cross-linguistic annotation projection. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2559–2565, Copenhagen, Denmark. Association for Computational Linguistics. ↗
  19. Annemarie Friedrich and Alexis Palmer. 2014a. Automatic prediction of aspectual class of verbs in context. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 517–523, Baltimore, Maryland. Association for Computational Linguistics. find
  20. Annemarie Friedrich and Alexis Palmer. 2014b. Situation entity annotation. In Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop, pages 149–158, Dublin, Ireland. Association for Computational Linguistics and Dublin City University. find
  21. Annemarie Friedrich, Alexis Palmer, and Manfred Pinkal. 2016. Situation entity types: automatic classification of clause-level aspect. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1757–1768, Berlin, Germany. Association for Computational Linguistics. find
  22. Annemarie Friedrich, Nianwen Xue, and Alexis Palmer. 2023. A kind introduction to lexical and grammatical aspect, with a survey of computational approaches. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 599– 622, Dubrovnik, Croatia. Association for Computational Linguistics. ↗
  23. William Gantt, Lelia Glass, and Aaron Steven White. 2022. Decomposing and recomposing event structure. Transactions of the Association for Computational Linguistics, 10:17–34. ↗
  24. Barts Geurts. 1985. Generics. Journal of Semantics, 3(4):247–255. find
  25. Venkata Govindarajan, Benjamin Van Durme, and Aaron Steven White. 2019. Decomposing generalization: Models of generic, habitual, and episodic statements. Transactions of the Association for Computational Linguistics, 7:501–517. ↗
  26. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, ..., and Zhiyu Ma. 2024. The llama 3 herd of models. find
  27. Ralph Grishman and Beth Sundheim. 1996. Message Understanding Conference- 6: A brief history. In COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics. find
  28. Liesa Heuschkel. 2016. Automatic classification of lexical aspectual class using distributional and rule-based methods. Master’s thesis, Saarland University. find
  29. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. find
  30. Joan B. Hooper. 1975. On assertive predicates. Syntax and Semantics, 4:91–124. ↗
  31. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. find
  32. Nancy Ide, Collin Baker, Christiane Fellbaum, Charles Fillmore, and Rebecca Passonneau. 2008. MASC: the manually annotated subcorpus of American English. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). find
  33. Nancy Ide, Collin Baker, Christiane Fellbaum, and Rebecca Passonneau. 2010. The manually annotated sub-corpus: A community resource for and by the people. In Proceedings of the ACL 2010 Conference Short Papers, pages 68–73, Uppsala, Sweden. Association for Computational Linguistics. find
  34. Lauri Karttunen. 1971. Implicative verbs. Language, pages 340–358. find
  35. Jan-Christoph Klie, Michael Bugert, Beto Boullosa, Richard Eckart de Castilho, and Iryna Gurevych. 2018. The inception platform: Machine-assisted and knowledge-oriented interactive annotation. In Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations, pages 5–9. Association for Computational Linguistics. Event Title: The 27th International Conference on Computational Linguistics (COLING 2018). find
  36. Thomas Kober, Malihe Alikhani, Matthew Stone, and Mark Steedman. 2020. Aspectuality across genre: A distributional semantics approach. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4546–4562, Barcelona, Spain (Online). International Committee on Computational Linguistics. ↗
  37. Natalia V. Kondratenko, Anastasiia A. Kiselova, and Liubov V. Zavalska. 2020. Strategies and tactics of communication in parliamentary discourse. studies about languages, 36:17–29. find
  38. Manfred Krifka, Francis J Pelletier, Gregory N Carlson, Gennaro Chierchia, Godehard Link, and Alice ter Meulen. 1995. Genericity: An introduction. In The Generic Book, pages 1–24. University of Chicago Press, Chicago and London. find
  39. J Richard Landis and Gary G Koch. 1977. The measurement of observer agreement for categorical data. Biometrics, pages 159–174. find
  40. Sarah-Jane Leslie. 2014. Carving up the social world with generics. Oxford studies in experimental philosophy, 1:208–232. ↗
  41. Sharid Loáiciga and Cristina Grisot. 2016. Predicting and using a pragmatic component of lexical aspect of simple past verbal tenses for improving English-to-French machine translation. Linguistic Issues in Language Technology, 13(3). find our card
  42. Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. PEFT: State-of-the-art parameter-efficient fine-tuning methods. https://github.com/huggingface/peft. ↗
  43. Kleio-Isidora Mavridou. 2016. Situation entity types: a cross-linguistic corpus study and a comparison of automatic classifiers. Master’s thesis, Institute for Computational Linguistics at Saarland University, Germany. find
  44. Kleio-Isidora Mavridou, Annemarie Friedrich, Melissa Peate Sørensen, Alexis Palmer, and Manfred Pinkal. 2015. Linking discourse modes and situation entity types in a cross-linguistic corpus study. In Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics, pages 12–21, Lisbon, Portugal. Association for Computational Linguistics. find
  45. Leland McInnes, John Healy, and Steve Astels. 2017. hdbscan: Hierarchical density based clustering. Journal of Open Source Software, 2(11):205. find our card
  46. Leland McInnes, John Healy, Nathaniel Saul, and Lukas Großberger. 2018. Umap: Uniform manifold approximation and projection. Journal of Open Source Software, 3(29):861. ↗
  47. Gustavo Novoa, Margaret Echelbarger, Andrew Gelman, and Susan A. Gelman. 2023. Generically partisan: Polarization in political communication. Proceedings of the National Academy of Sciences, 120(47):e2309361120. ↗
  48. Alexis Palmer, Elias Ponvert, Jason Baldridge, and Carlota Smith. 2007. A sequencing model for situation entity classification. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 896–903, Prague, Czech Republic. Association for Computational Linguistics. find
  49. Alexis Palmer and Caroline Sporleder. 2009. Situation entities and genre distinctions in the Penn Discourse TreeBank (abstract). find our card
  50. Rebecca Passonneau. 2006. Measuring agreement on set-valued items (MASI) for semantic and pragmatic annotation. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA). find our card
  51. Roma Patel and Ellie Pavlick. 2021. “Was it “stated” or was it “claimed”?: How linguistic bias affects generative language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10080– 10095, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  52. Jan Pfister, Julia Wunderle, and Andreas Hotho. 2025. LLäMmlein: Transparent, compact and competitive German-only language models from scratch. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2227–2246, Vienna, Austria. Association for Computational Linguistics. find
  53. Barbara Plank. 2022. The “problem” of human label variation: On ground truth in data, modeling and evaluation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10671–10682, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. ↗ our card
  54. Günter Radden. 2009. Generic reference in English: A metonymic and conceptual blending analysis. In Klaus-Uwe Panther, Linda L. Thornburg, and Antonio Barcelona, editors, Metonymy and Metaphor in Grammar, pages 199–228. John Benjamins Publishing Company. ↗
  55. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. find
  56. Tom Ralston. 2024. Reconceptualising the psychological theory of generics. Philosophical Studies, 181:2973–2995. ↗
  57. Marta Recasens, Cristian Danescu-Niculescu-Mizil, and Dan Jurafsky. 2013. Linguistic models for analyzing and detecting biased language. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1650–1659, Sofia, Bulgaria. Association for Computational Linguistics. find
  58. Ines Rehbein, Josef Ruppenhofer, Annelen Brunner, and Simone Paolo Ponzetto. 2024. Out of the mouths of MPs: Speaker attribution in parliamentary debates. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12553–12563, Torino, Italia. ELRA and ICCL. find
  59. Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe, and Francis Ferraro. 2021. Discriminative and generative transformer-based models for situation entity classification. ↗
  60. Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, ..., and Mojtaba Seyedhosseini. 2025. Embeddinggemma: Powerful and lightweight text representations. find
  61. Carlota S. Smith. 1983. A theory of aspectual choice. Language, 59(3):479–501. ↗
  62. Carlota S. Smith. 1991. The Parameter of Aspect. Kluwer. ↗
  63. Carlota S. Smith. 2003. Modes of Discourse: The Local Structure of Texts. Cambridge Studies in Linguistics. Cambridge University Press. find
  64. Carlota S Smith. 2005. Aspectual entities and tense in discourse, pages 223–237. Springer. find
  65. Max Upravitelev, Nicolau Duran-Silva, Christian Woerle, Giuseppe Guarino, Salar Mohtaj, Jing Yang, Veronika Solopova, and Vera Schmitt. 2025. Comparing LLMs and BERT-based classifiers for resource-sensitive claim verification in social media. In Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025), pages 281–287, Vienna, Austria. Association for Computational Linguistics. find
  66. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  67. Zeno Vendler. 1967. Linguistics in Philosophy. Cornell University Press. ↗
  68. R. Kent Weaver. 1986. The politics of blame avoidance. Journal of Public Policy, 6(4):371–398. 9. ↗
  69. Language Resource References Andreas Blaette. 2017. GermaParl. Corpus of Plenary Protocols of the German Bundestag. find

↑ back to top