14 citations · 22 across the 5 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 5 cited
PAC-Bayesian Contrastive Unsupervised Representation Learning
Kento Nozawa, Pascal Germain, Benjamin Guedj
Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data. While CURL has colle…
cs.LG2019★ 2 cited
PAC-Bayes Analysis of Sentence Representation
Kento Nozawa, Issei Sato
Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristi…