papers AI Learner
The Github is limit! Click to go to the new site.

PAC-Bayes Analysis of Sentence Representation

2019-02-12
Kento Nozawa, Issei Sato

Abstract

Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristics using pre-trained word vectors are widely applied to machine learning tasks. However, they are not well understood from a theoretical perspective. We analyze learning sentence vectors from a transfer learning perspective by using a PAC-Bayes bound that enables us to understand existing heuristics. We show that simple heuristics such as averaging and inverse document frequency weighted averaging are derived by our formulation. Moreover, we propose novel sentence vector learning algorithms on the basis of our PAC-Bayes analysis.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.04247

PDF

http://arxiv.org/pdf/1902.04247


Similar Posts

Comments