Research & Publications
2023
Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
arXiv:2302.12979
2023
Paper
2022
2021
Self-Learning for Zero-Shot Neural Machine Translation 🏆 Best Paper
LoResMT @ MT Summit 2021
2021
Paper
2020
Multilingual and Customized Neural Machine Translation Thesis
PhD Thesis, University of Trento & FBK HLT-MT Lab | Advised by Marcello Federico
My doctoral thesis investigates approaches to improve the performance of neural machine translation models for language pairs without large-scale training data. This work explores zero-shot translation, verbosity control, and isochrony-aware models for automatic dubbing.
2019
2018
A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
COLING 2018
2018
Paper
Adapting Multilingual NMT to Extremely Low Resource Languages: FBK's Participation in the Basque-English Low-Resource MT Task
IWSLT 2018
2018
Paper
2017
Improving Zero-Shot Translation of Low-Resource Languages 🏆 Best Paper
IWSLT 2017
2015
Multi-Camera Multi-Target Tracking Using Relaxation Processes Thesis
MSc Thesis, Ca' Foscari University of Venice | Advised by Marcello Pelillo & Andrea Prati
My masters thesis focuses on multi-camera, multi-target tracking framed as a game-theoretic relaxation labeling problem. Targets are detected via a probabilistic occupancy map, then consistently labeled across views using a replicated-labels extension to handle limited cross-camera visibility.
Patents
Systems, Methods, and Apparatuses for Controlling Output Length in Neural Machine Translation Patent
US Patent 11,295,081
2022
Paper