A. (Arianna) Bisazza, PhD

Associate Professor

Faculty of Arts

Telephone:

+31 50 36 35858

E-mail:

a.bisazza rug.nl

Homepage Research Portal

Publications

A Primer on the Inner Workings of Transformer-based Language Models

Ferrando, J., Sarti, G., Bisazza, A. & Costa-jussà, M., 30-Apr-2024.

Research output: Working paper › Preprint › Academic

Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation

Edman, L., Sarti, G., Toral, A., van Noord, G. & Bisazza, A., 16-Apr-2024, In: Transactions of the Association for Computational Linguistics. 12, p. 392-410 19 p.

Research output: Contribution to journal › Article › Academic › peer-review

Democratizing Advanced Attribution Analyses of Generative Language Models with the Inseq Toolkit

Sarti, G., Feldhus, N., Qi, J., Nissim, M. & Bisazza, A., 2024, xAI-2024 Late-breaking Work, Demos and Doctoral Consortium Joint Proceedings. Longo, L., Liu, W. & Montavon, G. (eds.). CEUR Workshop Proceedings (CEUR-WS.org), p. 289-296 8 p. (CEUR Workshop Proceedings; vol. 3793).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Encoding of lexical tone in self-supervised models of spoken language

Shen, G., Watkins, M., Alishahi, A., Bisazza, A. & Chrupała, G., 2024, The 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Proceedings of the Conference Volume 1: Long Papers. Duh, K., Gomez, H. & Bethard, S. (eds.). Association for Computational Linguistics (ACL), Vol. 1. p. 4250-4261

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Endowing Neural Language Learners with Human-like Biases: A Case Study on Dependency Length Minimization

Zhang, Y., Verhoef, T., van Noord, G. & Bisazza, A., May-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. (eds.). ELRA and ICCL, p. 5819-5832 14 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

Qi, J., Sarti, G., Fernández, R. & Bisazza, A., 19-Jun-2024.

Research output: Working paper › Preprint › Academic

Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off

Lian, Y., Bisazza, A. & Verhoef, T., 2023, In: Transactions of the Association for Computational Linguistics. 11, p. 1033-1047 15 p.

Research output: Contribution to journal › Article › Academic › peer-review

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models

Qi, J., Fernández, R. & Bisazza, A., 2023, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Bouamor, H., Pino, J. & Bali, K. (eds.). Association for Computational Linguistics, ACL Anthology, p. 10650-10666 17 p.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Inseq: An Interpretability Toolkit for Sequence Generation Models

Sarti, G., Feldhus, N., Sickert, L., Wal, O. V. D., Nissim, M. & Bisazza, A., 27-Feb-2023, arXiv.

Research output: Working paper › Preprint › Academic

Inseq: An Interpretability Toolkit for Sequence Generation Models

Sarti, G., Feldhus, N., Sickert, L., Wal, O. V. D., Nissim, M. & Bisazza, A., Jul-2023, p. 421-435. 14 p.

Research output: Contribution to conference › Paper › Academic

All (55) publications

View full research profile