A Bayesian Multilingual Document Model for Zero-shot Topic Identification and Discovery

arXiv:2007.01359v3 Announce Type: replace
Abstract: In this paper, we present a Bayesian multilingual document model for learning language-independent document embeddings. The model is an extension of BaySMM [Kesiraju et al 2020] to the multilingual scenario. It learns to represent the document embeddings in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. We propagate the learned uncertainties through linear classifiers that benefit zero-shot cross-lingual topic identification. Our experiments on 17 languages show that the proposed multilingual Bayesian …

abstract arxiv bayesian cs.cl discovery document embeddings extension form identification independent language multilingual paper type zero-shot