G. (Gabriele) Sarti, MSc

Promovendus in computationele taalkunde

Telefoon:

E-mail:

g.sarti rug.nl

Research interests

My research interests focus on interpretability for NLP models, in particular to the benefit of end-users and by leveraging human behavioral signals. I am also passionate about social applications of machine learning, ethical AI, and open source collaboration.

My PhD project, conducted under the supervision of Arianna Bisazza and Malvina Nissim, aims to empower users of neural machine translation systems by developing interpretable and interactive tools for more efficient professional post-editing.

Publicaties

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

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

Onderzoeksoutput: Voordruk ›

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, blz. 392-410 19 blz.

Onderzoeksoutput › › peer review

IT5: Text-to-text Pretraining for Italian Language Understanding and Generation

Sarti, G. & Nissim, M., 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. (uitgave). European Language Resources Association (ELRA), blz. 9422-9433 12 blz.

Onderzoeksoutput › › peer review

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

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

Onderzoeksoutput: Voordruk ›

Contrastive Language-Image Pre-training for the Italian Language

Bianchi, F., Attanasio, G., Pisoni, R., Terragni, S., Sarti, G. & Balestri, D., 2023, Proceedings of the 9th Italian Conference on Computational Linguistics. Boschetti, F., Lebani, G. E., Magnini, B. & Novielli, N. (uitgave). CEUR Workshop Proceedings (CEUR-WS.org), 8 blz. (CEUR Workshop Proceedings; vol. 3596).

Onderzoeksoutput › › peer review

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

Langedijk, A., Mohebbi, H., Sarti, G., Zuidema, W. & Jumelet, J., 5-okt.-2023, arXiv.

Onderzoeksoutput: Voordruk ›

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.

Onderzoeksoutput: Voordruk ›

Inseq: An Interpretability Toolkit for Sequence Generation Models

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

Onderzoeksoutput ›

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

Sarti, G., Chrupała, G., Nissim, M. & Bisazza, A., 2-okt.-2023, arXiv.

Onderzoeksoutput: Voordruk ›

RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

Sarti, G., Htut, P. M., Niu, X., Hsu, B., Currey, A., Dinu, G. & Nadejde, M., jul.-2023, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Rogers, A., Boyd-Graber, J. & Okazaki, N. (uitgave). Toronto, ON, CA: Association for Computational Linguistics (ACL), Vol. 2. blz. 1476-1490 14 blz.

Onderzoeksoutput › › peer review

Lees meer