← Search

Roberto Cavicchioli

2 accepted papers

2024

Learning from Wrong Predictions in Low-Resource Neural Machine Translation

COLING 2024main

Resource scarcity in Neural Machine Translation is a challenging problem in both industry applications and in the support of less-spoken languages represented, in the worst case, by endangered and low-resource languages. Many Data Augmentation methods rely on additional linguistic sources and softwa…

Cited by 1SourcePDFScholar
2024

ShareBERT: Embeddings Are Capable of Learning Hidden Layers

AAAI 2024technical

The deployment of Pre-trained Language Models in memory-limited devices is hindered by their massive number of parameters, which motivated the interest in developing smaller architectures. Established works in the model compression literature showcased that small models often present a noticeable pe…