123 citations · 125 across the 3 of their papers we have counts for
2 papers
cs.LG2022
Improving Generalization via Uncertainty Driven Perturbations
Matteo Pagliardini, Gilberto Manunza, Martin Jaggi +2
Recently Shah et al., 2020 pointed out the pitfalls of the simplicity bias - the tendency of gradient-based algorithms to learn simple models - which include the model's high sensi…
cs.CL2019★ 2 cited
Better Word Embeddings by Disentangling Contextual n-Gram Information
Prakhar Gupta, Matteo Pagliardini, Martin Jaggi
Pre-trained word vectors are ubiquitous in Natural Language Processing applications. In this paper, we show how training word embeddings jointly with bigram and even trigram embedd…