PUB - Publikationen an der Universität Bielefeld

Alle markieren

• [12]
  

  2025 | Preprint | PUB-ID: 3001572

  Bunzeck, B., Duran, D., Zarrieß, S.: Do Construction Distributions Shape Formal Language Learning In German BabyLMs? arXiv:2503.11593. (2025).

  PUB | PDF | DOI | arXiv
   
• [11]
  

  2025 | Preprint | PUB-ID: 3000929

  Bunzeck, B., Zarrieß, S.: Subword models struggle with word learning, but surprisal hides it. arXiv:2502.12835. (2025).

  PUB | PDF | DOI | arXiv
   
• [10]
  

  2025 | Konferenzbeitrag | PUB-ID: 3000275

  Bunzeck, B., Duran, D., Schade, L., Zarrieß, S.: Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas. In: Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B.D., and Schockaert, S. (eds.) Proceedings of the 31st International Conference on Computational Linguistics. p. 6039-6048. Association for Computational Linguistics, Abu Dhabi, UAE (2025).

  PUB | PDF | Download (ext.)
   
• [9]
  

  2024 | Konferenzbeitrag | PUB-ID: 3001254

  Bunzeck, B., Duran, D., Schade, L., Zarrieß, S.: Graphemes vs. phonemes: battling it out in character-based language models. In: Hu, M.Y., Mueller, A., Ross, C., Williams, A., Linzen, T., Zhuang, C., Choshen, L., Cotterell, R., Warstadt, A., and Wilcox, E.G. (eds.) The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning. p. 54-64. Association for Computational Linguistics, Miami, FL, USA (2024).

  PUB | PDF | Download (ext.)
   
• [8]
  

  2024 | Konferenzbeitrag | PUB-ID: 2993430

  Bunzeck, B., Zarrieß, S.: Fifty shapes of BLiMP: syntactic learning curves in language models are not uniform, but sometimes unruly. In: Qiu, A., Noble, B., Pagmar, D., Maraev, V., and Ilinykh, N. (eds.) Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning. p. 39-55. Association for Computational Linguistics, Kerrville, TX (2024).

  PUB | PDF | Download (ext.)
   
• [7]
  

  2024 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2999608

  Bunzeck, B., Diessel, H.: The richness of the stimulus: Constructional variation and development in child-directed speech. First Language. (2024).

  PUB | DOI
   
• [6]
  

  2024 | Konferenzbeitrag | PUB-ID: 2994136

  Bunzeck, B., Zarrieß, S.: The SlayQA benchmark of social reasoning: testing gender-inclusive generalization with neopronouns. In: Hupkes, D., Dankers, V., Batsuren, K., Kazemnejad, A., Christodoulopoulos, C., Giulianelli, M., and Cotterell, R. (eds.) Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP. p. 42-53. Association for Computational Linguistics, Miami, Florida, USA (2024).

  PUB | Download (ext.)
   
• [5]
  

  2023 | Datenpublikation | PUB-ID: 2993810

  Wojcik, P., Bunzeck, B., Zarrieß, S.: Replication Data for: "The Wikipedia Republic of Literary Characters". Harvard Dataverse (2023).

  PUB | Dateien verfügbar | DOI
   
• [4]
  

  2023 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2980942

  Wojcik, P., Bunzeck, B., Zarrieß, S.: The Wikipedia Republic of Literary Characters. Journal of Cultural Analytics. 8, (2023).

  PUB | PDF | DOI
   
• [3]
  

  2023 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2985109

  Bunzeck, B., Zarrieß, S.: GPT-wee: How Small Can a Small Language Model Really Get? In: Warstadt, A., Mueller, A., Choshen, L., Wilcox, E., Zhuang, C., Ciro, J., Mosquera, R., Paranjabe, B., Williams, A., Linzen, T., and Cotterell, R. (eds.) Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning. p. 35-46. Association for Computational Linguistics, Stroudsburg, PA (2023).

  PUB | PDF | DOI | Download (ext.)
   
• [2]
  

  2023 | Zeitschriftenaufsatz | Veröffentlicht | PUB-ID: 2980943

  Druskat, S., Krause, T., Lachenmaier, C., Bunzeck, B.: Hexatomic: An extensible, OS-independent platform fordeep multi-layer linguistic annotation of corpora. Journal of Open Source Software. 8, : 4825 (2023).

  PUB | PDF | DOI
   
• [1]
  

  2023 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2982902

  Bunzeck, B., Zarrieß, S.: Entrenchment Matters: Investigating Positional and Constructional Sensitivity in Small and Large Language Models. In: Breitholtz, E., Lappin, S., Loaiciga, S., Ilinykh, N., and Dobnik, S. (eds.) Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD). p. 25-37. Association for Computational Linguistics, Stroudsburg, PA (2023).

  PUB | PDF